Kevin Gimpel


2023

pdf bib
The Benefits of Label-Description Training for Zero-Shot Text Classification
Lingyu Gao | Debanjan Ghosh | Kevin Gimpel
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to further improve zero-shot accuracies with minimal effort. We curate small finetuning datasets intended to describe the labels for a task. Unlike typical finetuning data, which has texts annotated with labels, our data simply describes the labels in language, e.g., using a few related terms, dictionary/encyclopedia entries, and short templates. Across a range of topic and sentiment datasets, our method is more accurate than zero-shot by 17-19% absolute. It is also more robust to choices required for zero-shot classification, such as patterns for prompting the model to classify and mappings from labels to tokens in the model’s vocabulary. Furthermore, since our data merely describes the labels but does not use input texts, finetuning on it yields a model that performs strongly on multiple text domains for a given label set, even improving over few-shot out-of-domain classification in multiple settings.

2022

pdf bib
Baked-in State Probing
Shubham Toshniwal | Sam Wiseman | Karen Livescu | Kevin Gimpel
Findings of the Association for Computational Linguistics: EMNLP 2022

Neural language models have been analyzed for their linguistic and extra-linguistic knowledge via probing. Of particular interest has been the following question: how much can a language model trained only on form learn about meaning? Recent work has demonstrated via probing classifiers that in the setting of simple procedural text, where by “meaning” we mean the underlying world state, language models have a non-trivial performance on world state tracking. However, our proposed evaluation based on model predictions shows differing results, suggesting that these models are either not capturing the world state or not using it. How do these results change if the model has access to the world state? We explore this alternate setting with access to the underlying world state only during training and investigate ways of “baking in” the state knowledge along with the primary task of language modeling. Our proposed approaches allow for state probing during inference simply via text prompts, avoiding any probing classifier machinery. In terms of performance, we show that baking in the state knowledge during training leads to significant improvements in state tracking performance and text generation quality,

pdf bib
“What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation
Lingyu Gao | Debanjan Ghosh | Kevin Gimpel
Proceedings of the 11th Joint Conference on Lexical and Computational Semantics

We propose a type-controlled framework for inquisitive question generation. We annotate an inquisitive question dataset with question types, train question type classifiers, and finetune models for type-controlled question generation. Empirical results demonstrate that we can generate a variety of questions that adhere to specific types while drawing from the source texts. We also investigate strategies for selecting a single question from a generated set, considering both an informative vs. inquisitive question classifier and a pairwise ranker trained from a small set of expert annotations. Question selection using the pairwise ranker yields strong results in automatic and manual evaluation. Our human evaluation assesses multiple aspects of the generated questions, finding that the ranker chooses questions with the best syntax (4.59), semantics (4.37), and inquisitiveness (3.92) on a scale of 1-5, even rivaling the performance of human-written questions.

pdf bib
Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing
Freda Shi | Kevin Gimpel | Karen Livescu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We present substructure distribution projection (SubDP), a technique that projects a distribution over structures in one domain to another, by projecting substructure distributions separately. Models for the target domain can then be trained, using the projected distributions as soft silver labels. We evaluate SubDP on zero shot cross-lingual dependency parsing, taking dependency arcs as substructures: we project the predicted dependency arc distributions in the source language(s) to target language(s), and train a target language parser on the resulting distributions. Given an English tree bank as the only source of human supervision, SubDP achieves better unlabeled attachment score than all prior work on the Universal Dependencies v2.2 (Nivre et al., 2020) test set across eight diverse target languages, as well as the best labeled attachment score on six languages. In addition, SubDP improves zero shot cross-lingual dependency parsing with very few (e.g., 50) supervised bitext pairs, across a broader range of target languages.

pdf bib
SummScreen: A Dataset for Abstractive Screenplay Summarization
Mingda Chen | Zewei Chu | Sam Wiseman | Kevin Gimpel
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We introduce SummScreen, a summarization dataset comprised of pairs of TV series transcripts and human written recaps. The dataset provides a challenging testbed for abstractive summarization for several reasons. Plot details are often expressed indirectly in character dialogues and may be scattered across the entirety of the transcript. These details must be found and integrated to form the succinct plot descriptions in the recaps. Also, TV scripts contain content that does not directly pertain to the central plot but rather serves to develop characters or provide comic relief. This information is rarely contained in recaps. Since characters are fundamental to TV series, we also propose two entity-centric evaluation metrics. Empirically, we characterize the dataset by evaluating several methods, including neural models and those based on nearest neighbors. An oracle extractive approach outperforms all benchmarked models according to automatic metrics, showing that the neural models are unable to fully exploit the input transcripts. Human evaluation and qualitative analysis reveal that our non-oracle models are competitive with their oracle counterparts in terms of generating faithful plot events and can benefit from better content selectors. Both oracle and non-oracle models generate unfaithful facts, suggesting future research directions.

pdf bib
Paraphrastic Representations at Scale
John Wieting | Kevin Gimpel | Graham Neubig | Taylor Berg-kirkpatrick
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We release trained models for English, Arabic, German, Spanish, French, Russian, Turkish, and Chinese. We train these models on large amounts of data, achieving significantly improved performance from our original papers on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks. Moreover, the resulting models surpass all prior work on efficient unsupervised semantic textual similarity, even significantly outperforming supervised BERT-based models like Sentence-BERT (Reimers and Gurevych, 2019). Most importantly, our models are orders of magnitude faster than other strong similarity models and can be used on CPU with little difference in inference speed (even improved speed over GPU when using more CPU cores), making these models an attractive choice for users without access to GPUs or for use on embedded devices. Finally, we add significantly increased functionality to the code bases for training paraphrastic sentence models, easing their use for both inference and for training them for any desired language with parallel data. We also include code to automatically download and preprocess training data.

2021

pdf bib
WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
Mingda Chen | Sam Wiseman | Kevin Gimpel
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Substructure Substitution: Structured Data Augmentation for NLP
Haoyue Shi | Karen Livescu | Kevin Gimpel
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Unsupervised Label Refinement Improves Dataless Text Classification
Zewei Chu | Karl Stratos | Kevin Gimpel
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Reconsidering the Past: Optimizing Hidden States in Language Models
Davis Yoshida | Kevin Gimpel
Findings of the Association for Computational Linguistics: EMNLP 2021

We present Hidden-State Optimization (HSO), a gradient-based method for improving the performance of transformer language models at inference time. Similar to dynamic evaluation (Krause et al., 2018), HSO computes the gradient of the log-probability the language model assigns to an evaluation text, but uses it to update the cached hidden states rather than the model parameters. We test HSO with pretrained Transformer-XL and GPT-2 language models, finding improvement on the WikiText-103 and PG-19 datasets in terms of perplexity, especially when evaluating a model outside of its training distribution. We also demonstrate downstream applicability by showing gains in the recently developed prompt-based few-shot evaluation setting, again with no extra parameters or training data.

pdf bib
FlowPrior: Learning Expressive Priors for Latent Variable Sentence Models
Xiaoan Ding | Kevin Gimpel
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Variational autoencoders (VAEs) are widely used for latent variable modeling of text. We focus on variations that learn expressive prior distributions over the latent variable. We find that existing training strategies are not effective for learning rich priors, so we propose adding the importance-sampled log marginal likelihood as a second term to the standard VAE objective to help when learning the prior. Doing so improves results for all priors evaluated, including a novel choice for sentence VAEs based on normalizing flows (NF). Priors parameterized with NF are no longer constrained to a specific distribution family, allowing a more flexible way to encode the data distribution. Our model, which we call FlowPrior, shows a substantial improvement in language modeling tasks compared to strong baselines. We demonstrate that FlowPrior learns an expressive prior with analysis and several forms of evaluation involving generation.

pdf bib
On Generalization in Coreference Resolution
Shubham Toshniwal | Patrick Xia | Sam Wiseman | Karen Livescu | Kevin Gimpel
Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference

While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains. We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the off-the-shelf performance of models. We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models. This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results.

2020

pdf bib
An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
Lifu Tu | Tianyu Liu | Kevin Gimpel
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Many tasks in natural language processing involve predicting structured outputs, e.g., sequence labeling, semantic role labeling, parsing, and machine translation. Researchers are increasingly applying deep representation learning to these problems, but the structured component of these approaches is usually quite simplistic. In this work, we propose several high-order energy terms to capture complex dependencies among labels in sequence labeling, including several that consider the entire label sequence. We use neural parameterizations for these energy terms, drawing from convolutional, recurrent, and self-attention networks. We use the framework of learning energy-based inference networks (Tu and Gimpel, 2018) for dealing with the difficulties of training and inference with such models. We empirically demonstrate that this approach achieves substantial improvement using a variety of high-order energy terms on four sequence labeling tasks, while having the same decoding speed as simple, local classifiers. We also find high-order energies to help in noisy data conditions.

pdf bib
On the Role of Supervision in Unsupervised Constituency Parsing
Haoyue Shi | Karen Livescu | Kevin Gimpel
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.

pdf bib
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference
Xiaoan Ding | Tianyu Liu | Baobao Chang | Zhifang Sui | Kevin Gimpel
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural language inference (NLI). We propose GenNLI, a generative classifier for NLI tasks, and empirically characterize its performance by comparing it to five baselines, including discriminative models and large-scale pretrained language representation models like BERT. We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work (Lewis and Fan, 2019). In particular, we find strong results with a simple unbounded modification to log loss, which we call the “infinilog loss”. Our experiments show that GenNLI outperforms both discriminative and pretrained baselines across several challenging NLI experimental settings, including small training sets, imbalanced label distributions, and label noise.

pdf bib
Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks
Shubham Toshniwal | Sam Wiseman | Allyson Ettinger | Karen Livescu | Kevin Gimpel
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Long document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference resolution using just the global representation of entities shows practical benefits but requires keeping all entities in memory, which can be impractical for long documents. We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time, thus guaranteeing a linear runtime in length of document. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy

pdf bib
Learning Probabilistic Sentence Representations from Paraphrases
Mingda Chen | Kevin Gimpel
Proceedings of the 5th Workshop on Representation Learning for NLP

Probabilistic word embeddings have shown effectiveness in capturing notions of generality and entailment, but there is very little work on doing the analogous type of investigation for sentences. In this paper we define probabilistic models that produce distributions for sentences. Our best-performing model treats each word as a linear transformation operator applied to a multivariate Gaussian distribution. We train our models on paraphrases and demonstrate that they naturally capture sentence specificity. While our proposed model achieves the best performance overall, we also show that specificity is represented by simpler architectures via the norm of the sentence vectors. Qualitative analysis shows that our probabilistic model captures sentential entailment and provides ways to analyze the specificity and preciseness of individual words.

pdf bib
A Cross-Task Analysis of Text Span Representations
Shubham Toshniwal | Haoyue Shi | Bowen Shi | Lingyu Gao | Karen Livescu | Kevin Gimpel
Proceedings of the 5th Workshop on Representation Learning for NLP

Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive research has focused on functional architectures for representing words and sentences, there is less work on representing arbitrary spans of text within sentences. In this paper, we conduct a comprehensive empirical evaluation of six span representation methods using eight pretrained language representation models across six tasks, including two tasks that we introduce. We find that, although some simple span representations are fairly reliable across tasks, in general the optimal span representation varies by task, and can also vary within different facets of individual tasks. We also find that the choice of span representation has a bigger impact with a fixed pretrained encoder than with a fine-tuned encoder.

pdf bib
Mining Knowledge for Natural Language Inference from Wikipedia Categories
Mingda Chen | Zewei Chu | Karl Stratos | Kevin Gimpel
Findings of the Association for Computational Linguistics: EMNLP 2020

Accurate lexical entailment (LE) and natural language inference (NLI) often require large quantities of costly annotations. To alleviate the need for labeled data, we introduce WikiNLI: a resource for improving model performance on NLI and LE tasks. It contains 428,899 pairs of phrases constructed from naturally annotated category hierarchies in Wikipedia. We show that we can improve strong baselines such as BERT and RoBERTa by pretraining them on WikiNLI and transferring the models on downstream tasks. We conduct systematic comparisons with phrases extracted from other knowledge bases such as WordNet and Wikidata to find that pretraining on WikiNLI gives the best performance. In addition, we construct WikiNLI in other languages, and show that pretraining on them improves performance on NLI tasks of corresponding languages.

pdf bib
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Lifu Tu | Richard Yuanzhe Pang | Sam Wiseman | Kevin Gimpel
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference network (Tu and Gimpel, 2018) trained to minimize the autoregressive teacher energy. This contrasts with the popular approach of training a non-autoregressive model on a distilled corpus consisting of the beam-searched outputs of such a teacher model. Our approach, which we call ENGINE (ENerGy-based Inference NEtworks), achieves state-of-the-art non-autoregressive results on the IWSLT 2014 DE-EN and WMT 2016 RO-EN datasets, approaching the performance of autoregressive models.

pdf bib
PeTra: A Sparsely Supervised Memory Model for People Tracking
Shubham Toshniwal | Allyson Ettinger | Kevin Gimpel | Karen Livescu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We propose PeTra, a memory-augmented neural network designed to track entities in its memory slots. PeTra is trained using sparse annotation from the GAP pronoun resolution dataset and outperforms a prior memory model on the task while using a simpler architecture. We empirically compare key modeling choices, finding that we can simplify several aspects of the design of the memory module while retaining strong performance. To measure the people tracking capability of memory models, we (a) propose a new diagnostic evaluation based on counting the number of unique entities in text, and (b) conduct a small scale human evaluation to compare evidence of people tracking in the memory logs of PeTra relative to a previous approach. PeTra is highly effective in both evaluations, demonstrating its ability to track people in its memory despite being trained with limited annotation.

pdf bib
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Lifu Tu | Richard Yuanzhe Pang | Kevin Gimpel
Proceedings of the Fourth Workshop on Structured Prediction for NLP

Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training “inference networks” to approximate structured inference instead of using gradient descent. However, their alternating optimization approach suffers from instabilities during training, requiring additional loss terms and careful hyperparameter tuning. In this paper, we contribute several strategies to stabilize and improve this joint training of energy functions and inference networks for structured prediction. We design a compound objective to jointly train both cost-augmented and test-time inference networks along with the energy function. We propose joint parameterizations for the inference networks that encourage them to capture complementary functionality during learning. We empirically validate our strategies on two sequence labeling tasks, showing easier paths to strong performance than prior work, as well as further improvements with global energy terms.

pdf bib
Distractor Analysis and Selection for Multiple-Choice Cloze Questions for Second-Language Learners
Lingyu Gao | Kevin Gimpel | Arnar Jensson
Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications

We consider the problem of automatically suggesting distractors for multiple-choice cloze questions designed for second-language learners. We describe the creation of a dataset including collecting manual annotations for distractor selection. We assess the relationship between the choices of the annotators and features based on distractors and the correct answers, both with and without the surrounding passage context in the cloze questions. Simple features of the distractor and correct answer correlate with the annotations, though we find substantial benefit to additionally using large-scale pretrained models to measure the fit of the distractor in the context. Based on these analyses, we propose and train models to automatically select distractors, and measure the importance of model components quantitatively.

2019

pdf bib
Visually Grounded Neural Syntax Acquisition
Haoyue Shi | Jiayuan Mao | Kevin Gimpel | Karen Livescu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for learning syntactic representations and structures without any explicit supervision. The model learns by looking at natural images and reading paired captions. VG-NSL generates constituency parse trees of texts, recursively composes representations for constituents, and matches them with images. We define concreteness of constituents by their matching scores with images, and use it to guide the parsing of text. Experiments on the MSCOCO data set show that VG-NSL outperforms various unsupervised parsing approaches that do not use visual grounding, in terms of F1 scores against gold parse trees. We find that VGNSL is much more stable with respect to the choice of random initialization and the amount of training data. We also find that the concreteness acquired by VG-NSL correlates well with a similar measure defined by linguists. Finally, we also apply VG-NSL to multiple languages in the Multi30K data set, showing that our model consistently outperforms prior unsupervised approaches.

pdf bib
Beyond BLEU:Training Neural Machine Translation with Semantic Similarity
John Wieting | Taylor Berg-Kirkpatrick | Kevin Gimpel | Graham Neubig
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final translation accuracy. However, training with BLEU has some limitations: it doesn’t assign partial credit, it has a limited range of output values, and it can penalize semantically correct hypotheses if they differ lexically from the reference. In this paper, we introduce an alternative reward function for optimizing NMT systems that is based on recent work in semantic similarity. We evaluate on four disparate languages trans-lated to English, and find that training with our proposed metric results in better translations as evaluated by BLEU, semantic similarity, and human evaluation, and also that the optimization procedure converges faster. Analysis suggests that this is because the proposed metric is more conducive to optimization, assigning partial credit and providing more diversity in scores than BLEU

pdf bib
Simple and Effective Paraphrastic Similarity from Parallel Translations
John Wieting | Kevin Gimpel | Graham Neubig | Taylor Berg-Kirkpatrick
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating para-phrase corpora. Further, we show that the resulting model can be applied to cross lingual tasks where it both outperforms and is orders of magnitude faster than more complex state-of-the-art baselines.

pdf bib
Controllable Paraphrase Generation with a Syntactic Exemplar
Mingda Chen | Qingming Tang | Sam Wiseman | Kevin Gimpel
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled rather by a sentential exemplar. To evaluate quantitatively with standard metrics, we create a novel dataset with human annotations. We also develop a variational model with a neural module specifically designed for capturing syntactic knowledge and several multitask training objectives to promote disentangled representation learning. Empirically, the proposed model is observed to achieve improvements over baselines and learn to capture desirable characteristics.

pdf bib
PoMo: Generating Entity-Specific Post-Modifiers in Context
Jun Seok Kang | Robert Logan | Zewei Chu | Yang Chen | Dheeru Dua | Kevin Gimpel | Sameer Singh | Niranjan Balasubramanian
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, “Barack Obama, _______, supported the #MeToo movement.”, the phrase “a father of two girls” is a contextually relevant post-modifier. To this end, we build PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt a number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives a >20% improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research.

pdf bib
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations
Mingda Chen | Qingming Tang | Sam Wiseman | Kevin Gimpel
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentanglement between semantic and syntactic representations by training with multiple losses, including losses that exploit aligned paraphrastic sentences and word-order information. We evaluate our models on standard semantic similarity tasks and novel syntactic similarity tasks. Empirically, we find that the model with the best performing syntactic and semantic representations also gives rise to the most disentangled representations.

pdf bib
Benchmarking Approximate Inference Methods for Neural Structured Prediction
Lifu Tu | Kevin Gimpel
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Exact structured inference with neural network scoring functions is computationally challenging but several methods have been proposed for approximating inference. One approach is to perform gradient descent with respect to the output structure directly (Belanger and McCallum, 2016). Another approach, proposed recently, is to train a neural network (an “inference network”) to perform inference (Tu and Gimpel, 2018). In this paper, we compare these two families of inference methods on three sequence labeling datasets. We choose sequence labeling because it permits us to use exact inference as a benchmark in terms of speed, accuracy, and search error. Across datasets, we demonstrate that inference networks achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We find further benefit by combining inference networks and gradient descent, using the former to provide a warm start for the latter.

pdf bib
EntEval: A Holistic Evaluation Benchmark for Entity Representations
Mingda Chen | Zewei Chu | Yang Chen | Karl Stratos | Kevin Gimpel
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Rich entity representations are useful for a wide class of problems involving entities. Despite their importance, there is no standardized benchmark that evaluates the overall quality of entity representations. In this work, we propose EntEval: a test suite of diverse tasks that require nontrivial understanding of entities including entity typing, entity similarity, entity relation prediction, and entity disambiguation. In addition, we develop training techniques for learning better entity representations by using natural hyperlink annotations in Wikipedia. We identify effective objectives for incorporating the contextual information in hyperlinks into state-of-the-art pretrained language models (Peters et al., 2018) and show that they improve strong baselines on multiple EntEval tasks.

pdf bib
Latent-Variable Generative Models for Data-Efficient Text Classification
Xiaoan Ding | Kevin Gimpel
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et al., 2017; Lewis and Fan,2019). In this paper, we improve generative text classifiers by introducing discrete latent variables into the generative story, and explore several graphical model configurations. We parameterize the distributions using standard neural architectures used in conditional language modeling and perform learning by directly maximizing the log marginal likelihood via gradient-based optimization, which avoids the need to do expectation-maximization. We empirically characterize the performance of our models on six text classification datasets. The choice of where to include the latent variable has a significant impact on performance, with the strongest results obtained when using the latent variable as an auxiliary conditioning variable in the generation of the textual input. This model consistently outperforms both the generative and discriminative classifiers in small-data settings. We analyze our model by finding that the latent variable captures interpretable properties of the data, even with very small training sets.

pdf bib
Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations
Mingda Chen | Zewei Chu | Kevin Gimpel
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Prior work on pretrained sentence embeddings and benchmarks focus on the capabilities of stand-alone sentences. We propose DiscoEval, a test suite of tasks to evaluate whether sentence representations include broader context information. We also propose a variety of training objectives that makes use of natural annotations from Wikipedia to build sentence encoders capable of modeling discourse. We benchmark sentence encoders pretrained with our proposed training objectives, as well as other popular pretrained sentence encoders on DiscoEval and other sentence evaluation tasks. Empirically, we show that these training objectives help to encode different aspects of information in document structures. Moreover, BERT and ELMo demonstrate strong performances over DiscoEval with individual hidden layers showing different characteristics.

pdf bib
Generating Diverse Story Continuations with Controllable Semantics
Lifu Tu | Xiaoan Ding | Dong Yu | Kevin Gimpel
Proceedings of the 3rd Workshop on Neural Generation and Translation

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider several sentence attributes, including sentiment, length, predicates, frames, and automatically-induced clusters. Our empirical results demonstrate: (1) our framework is accurate in terms of generating outputs that match the target control values; (2) our model yields increased maximum metric scores compared to standard n-best list generation via beam search; (3) controlling generation with semantic frames leads to a stronger combination of diversity and quality than other control variables as measured by automatic metrics. We also conduct a human evaluation to assess the utility of providing multiple suggestions for creative writing, demonstrating promising results for the potential of controllable, diverse generation in a collaborative writing system.

pdf bib
Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer
Richard Yuanzhe Pang | Kevin Gimpel
Proceedings of the 3rd Workshop on Neural Generation and Translation

We consider the problem of automatically generating textual paraphrases with modified attributes or properties, focusing on the setting without parallel data (Hu et al., 2017; Shen et al., 2017). This setting poses challenges for evaluation. We show that the metric of post-transfer classification accuracy is insufficient on its own, and propose additional metrics based on semantic preservation and fluency as well as a way to combine them into a single overall score. We contribute new loss functions and training strategies to address the different metrics. Semantic preservation is addressed by adding a cyclic consistency loss and a loss based on paraphrase pairs, while fluency is improved by integrating losses based on style-specific language models. We experiment with a Yelp sentiment dataset and a new literature dataset that we propose, using multiple models that extend prior work (Shen et al., 2017). We demonstrate that our metrics correlate well with human judgments, at both the sentence-level and system-level. Automatic and manual evaluation also show large improvements over the baseline method of Shen et al. (2017). We hope that our proposed metrics can speed up system development for new textual transfer tasks while also encouraging the community to address our three complementary aspects of transfer quality.

2018

pdf bib
Quality Signals in Generated Stories
Manasvi Sagarkar | John Wieting | Lifu Tu | Kevin Gimpel
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics

We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence (“continuation”) in the story. We seek to identify what makes a story continuation interesting, relevant, and have high overall quality. We crowdsource annotations along these three criteria for the outputs of story continuation systems, design features, and train models to predict the annotations. Our trained scorer can be used as a rich feature function for story generation, a reward function for systems that use reinforcement learning to learn to generate stories, and as a partial evaluation metric for story generation.

pdf bib
Variational Sequential Labelers for Semi-Supervised Learning
Mingda Chen | Qingming Tang | Karen Livescu | Kevin Gimpel
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent variables to define the conditional probability of a word given its context, drawing inspiration from word prediction objectives commonly used in learning word embeddings. The labeler helps inject discriminative information into the latent space. We explore several latent variable configurations, including ones with hierarchical structure, which enables the model to account for both label-specific and word-specific information. Our models consistently outperform standard sequential baselines on 8 sequence labeling datasets, and improve further with unlabeled data.

pdf bib
Parsing Speech: a Neural Approach to Integrating Lexical and Acoustic-Prosodic Information
Trang Tran | Shubham Toshniwal | Mohit Bansal | Kevin Gimpel | Karen Livescu | Mari Ostendorf
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features using a convolutional neural network over energy and pitch trajectories coupled with an attention-based recurrent neural network that accepts text and prosodic features. We find that different types of acoustic-prosodic features are individually helpful, and together give statistically significant improvements in parse and disfluency detection F1 scores over a strong text-only baseline. For this study with known sentence boundaries, error analyses show that the main benefit of acoustic-prosodic features is in sentences with disfluencies, attachment decisions are most improved, and transcription errors obscure gains from prosody.

pdf bib
Adversarial Example Generation with Syntactically Controlled Paraphrase Networks
Mohit Iyyer | John Wieting | Kevin Gimpel | Luke Zettlemoyer
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with the desired syntax. We show it is possible to create training data for this task by first doing backtranslation at a very large scale, and then using a parser to label the syntactic transformations that naturally occur during this process. Such data allows us to train a neural encoder-decoder model with extra inputs to specify the target syntax. A combination of automated and human evaluations show that SCPNs generate paraphrases that follow their target specifications without decreasing paraphrase quality when compared to baseline (uncontrolled) paraphrase systems. Furthermore, they are more capable of generating syntactically adversarial examples that both (1) “fool” pretrained models and (2) improve the robustness of these models to syntactic variation when used to augment their training data.

pdf bib
Smaller Text Classifiers with Discriminative Cluster Embeddings
Mingda Chen | Kevin Gimpel
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. We propose variations that selectively assign additional parameters to words, which further improves accuracy while still remaining parameter-efficient.

pdf bib
ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations
John Wieting | Kevin Gimpel
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We describe ParaNMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs. We generated the pairs automatically by using neural machine translation to translate the non-English side of a large parallel corpus, following Wieting et al. (2017). Our hope is that ParaNMT-50M can be a valuable resource for paraphrase generation and can provide a rich source of semantic knowledge to improve downstream natural language understanding tasks. To show its utility, we use ParaNMT-50M to train paraphrastic sentence embeddings that outperform all supervised systems on every SemEval semantic textual similarity competition, in addition to showing how it can be used for paraphrase generation.

2017

pdf bib
Emergent Predication Structure in Hidden State Vectors of Neural Readers
Hai Wang | Takeshi Onishi | Kevin Gimpel | David McAllester
Proceedings of the 2nd Workshop on Representation Learning for NLP

A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets. We present experiments supporting the emergence of “predication structure” in the hidden state vectors of these readers. More specifically, we provide evidence that the hidden state vectors represent atomic formulas 𝛷c where 𝛷 is a semantic property (predicate) and c is a constant symbol entity identifier.

pdf bib
Learning to Embed Words in Context for Syntactic Tasks
Lifu Tu | Kevin Gimpel | Karen Livescu
Proceedings of the 2nd Workshop on Representation Learning for NLP

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic category, and semantic role. We explore simple, efficient token embedding models based on standard neural network architectures. We learn token embeddings on a large amount of unannotated text and evaluate them as features for part-of-speech taggers and dependency parsers trained on much smaller amounts of annotated data. We find that predictors endowed with token embeddings consistently outperform baseline predictors across a range of context window and training set sizes.

pdf bib
Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings
John Wieting | Kevin Gimpel
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We consider the problem of learning general-purpose, paraphrastic sentence embeddings, revisiting the setting of Wieting et al. (2016b). While they found LSTM recurrent networks to underperform word averaging, we present several developments that together produce the opposite conclusion. These include training on sentence pairs rather than phrase pairs, averaging states to represent sequences, and regularizing aggressively. These improve LSTMs in both transfer learning and supervised settings. We also introduce a new recurrent architecture, the Gated Recurrent Averaging Network, that is inspired by averaging and LSTMs while outperforming them both. We analyze our learned models, finding evidence of preferences for particular parts of speech and dependency relations.

pdf bib
Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task
Zheng Cai | Lifu Tu | Kevin Gimpel
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

We consider the ROC story cloze task (Mostafazadeh et al., 2016) and present several findings. We develop a model that uses hierarchical recurrent networks with attention to encode the sentences in the story and score candidate endings. By discarding the large training set and only training on the validation set, we achieve an accuracy of 74.7%. Even when we discard the story plots (sentences before the ending) and only train to choose the better of two endings, we can still reach 72.5%. We then analyze this “ending-only” task setting. We estimate human accuracy to be 78% and find several types of clues that lead to this high accuracy, including those related to sentiment, negation, and general ending likelihood regardless of the story context.

pdf bib
Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext
John Wieting | Jonathan Mallinson | Kevin Gimpel
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence pairs. We evaluate the paraphrase pairs by their ability to serve as training data for learning paraphrastic sentence embeddings. We find that the data quality is stronger than prior work based on bitext and on par with manually-written English paraphrase pairs, with the advantage that our approach can scale up to generate large training sets for many languages and domains. We experiment with several language pairs and data sources, and develop a variety of data filtering techniques. In the process, we explore how neural machine translation output differs from human-written sentences, finding clear differences in length, the amount of repetition, and the use of rare words.

pdf bib
Broad Context Language Modeling as Reading Comprehension
Zewei Chu | Hai Wang | Kevin Gimpel | David McAllester
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015). We focus here on the LAMBADA dataset (Paperno et al., 2016), a word prediction task requiring broader context than the immediate sentence. We view LAMBADA as a reading comprehension problem and apply comprehension models based on neural networks. Though these models are constrained to choose a word from the context, they improve the state of the art on LAMBADA from 7.3% to 49%. We analyze 100 instances, finding that neural network readers perform well in cases that involve selecting a name from the context based on dialogue or discourse cues but struggle when coreference resolution or external knowledge is needed.

2016

pdf bib
Mapping Unseen Words to Task-Trained Embedding Spaces
Pranava Swaroop Madhyastha | Mohit Bansal | Kevin Gimpel | Karen Livescu
Proceedings of the 1st Workshop on Representation Learning for NLP

pdf bib
UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement
Hua He | John Wieting | Kevin Gimpel | Jinfeng Rao | Jimmy Lin
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

pdf bib
Commonsense Knowledge Base Completion
Xiang Li | Aynaz Taheri | Lifu Tu | Kevin Gimpel
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Charagram: Embedding Words and Sentences via Character n-grams
John Wieting | Mohit Bansal | Kevin Gimpel | Karen Livescu
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Who did What: A Large-Scale Person-Centered Cloze Dataset
Takeshi Onishi | Hai Wang | Mohit Bansal | Kevin Gimpel | David McAllester
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf bib
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks
Hua He | Kevin Gimpel | Jimmy Lin
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Machine Comprehension with Syntax, Frames, and Semantics
Hai Wang | Mohit Bansal | Kevin Gimpel | David McAllester
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

pdf bib
A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment
Jing Wang | Mohit Bansal | Kevin Gimpel | Brian D. Ziebart | Clement T. Yu
Transactions of the Association for Computational Linguistics, Volume 3

Word sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are informed by the local context surrounding the ambiguous word. We also discuss unsupervised ways of enriching the original corpus in order to improve model performance, including using neural word embeddings and external corpora to expand the context of each data instance. We demonstrate significant improvements over the previous state-of-the-art, achieving the best results reported to date on the SemEval-2013 WSI task.

pdf bib
From Paraphrase Database to Compositional Paraphrase Model and Back
John Wieting | Mohit Bansal | Kevin Gimpel | Karen Livescu
Transactions of the Association for Computational Linguistics, Volume 3

The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the heuristic nature of the confidences and its necessarily incomplete coverage. We propose models to leverage the phrase pairs from the PPDB to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB’s internal scores while simultaneously improving its coverage. They allow for learning phrase embeddings as well as improved word embeddings. Moreover, we introduce two new, manually annotated datasets to evaluate short-phrase paraphrasing models. Using our paraphrase model trained using PPDB, we achieve state-of-the-art results on standard word and bigram similarity tasks and beat strong baselines on our new short phrase paraphrase tasks.

pdf bib
Deep Multilingual Correlation for Improved Word Embeddings
Ang Lu | Weiran Wang | Mohit Bansal | Kevin Gimpel | Karen Livescu
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2014

pdf bib
Tailoring Continuous Word Representations for Dependency Parsing
Mohit Bansal | Kevin Gimpel | Karen Livescu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features
Kevin Gimpel | Noah A. Smith
Computational Linguistics, Volume 40, Issue 2 - June 2014

pdf bib
Weakly-Supervised Learning with Cost-Augmented Contrastive Estimation
Kevin Gimpel | Mohit Bansal
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
A Systematic Exploration of Diversity in Machine Translation
Kevin Gimpel | Dhruv Batra | Chris Dyer | Gregory Shakhnarovich
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters
Olutobi Owoputi | Brendan O’Connor | Chris Dyer | Kevin Gimpel | Nathan Schneider | Noah A. Smith
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2012

pdf bib
Structured Ramp Loss Minimization for Machine Translation
Kevin Gimpel | Noah A. Smith
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Concavity and Initialization for Unsupervised Dependency Parsing
Kevin Gimpel | Noah A. Smith
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Word Salad: Relating Food Prices and Descriptions
Victor Chahuneau | Kevin Gimpel | Bryan R. Routledge | Lily Scherlis | Noah A. Smith
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2011

pdf bib
Part-of-Speech Tagging for Twitter: Annotation, Features, and Experiments
Kevin Gimpel | Nathan Schneider | Brendan O’Connor | Dipanjan Das | Daniel Mills | Jacob Eisenstein | Michael Heilman | Dani Yogatama | Jeffrey Flanigan | Noah A. Smith
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Quasi-Synchronous Phrase Dependency Grammars for Machine Translation
Kevin Gimpel | Noah A. Smith
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

pdf bib
The CMU-ARK German-English Translation System
Chris Dyer | Kevin Gimpel | Jonathan H. Clark | Noah A. Smith
Proceedings of the Sixth Workshop on Statistical Machine Translation

pdf bib
Generative Models of Monolingual and Bilingual Gappy Patterns
Kevin Gimpel | Noah A. Smith
Proceedings of the Sixth Workshop on Statistical Machine Translation

2010

pdf bib
Distributed Asynchronous Online Learning for Natural Language Processing
Kevin Gimpel | Dipanjan Das | Noah A. Smith
Proceedings of the Fourteenth Conference on Computational Natural Language Learning

pdf bib
Movie Reviews and Revenues: An Experiment in Text Regression
Mahesh Joshi | Dipanjan Das | Kevin Gimpel | Noah A. Smith
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

pdf bib
Softmax-Margin CRFs: Training Log-Linear Models with Cost Functions
Kevin Gimpel | Noah A. Smith
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

2009

pdf bib
Feature-Rich Translation by Quasi-Synchronous Lattice Parsing
Kevin Gimpel | Noah A. Smith
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
Cube Summing, Approximate Inference with Non-Local Features, and Dynamic Programming without Semirings
Kevin Gimpel | Noah A. Smith
Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009)

2008

pdf bib
Rich Source-Side Context for Statistical Machine Translation
Kevin Gimpel | Noah A. Smith
Proceedings of the Third Workshop on Statistical Machine Translation