Dani Yogatama


2023

pdf bib
Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
Yi Tay | Mostafa Dehghani | Samira Abnar | Hyung Chung | William Fedus | Jinfeng Rao | Sharan Narang | Vinh Tran | Dani Yogatama | Donald Metzler
Findings of the Association for Computational Linguistics: EMNLP 2023

There have been a lot of interest in the scaling properties of Transformer models. However, not much has been done on the front of investigating the effect of scaling properties of different inductive biases and model architectures. Do model architectures scale differently? If so, how does inductive bias affect scaling behaviour? How does this influence upstream (pretraining) and downstream (transfer)? This paper conducts a systematic study of scaling behaviour of ten diverse model architectures such as Transformers, Switch Transformers, Universal Transformers, Dynamic convolutions, Performers, and recently proposed MLP-Mixers. Via extensive experiments, we show that (1) architecture is an indeed an important consideration when performing scaling and (2) the best performing model can fluctuate at different scales. We believe that the findings outlined in this work has significant implications to how model architectures are currently evaluated in the community.

pdf bib
The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining
Ting-Rui Chiang | Dani Yogatama
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

We analyze the masked language modeling pretraining objective function from the perspective of the Distributional Hypothesis. We investigate whether the better sample efficiency and the better generalization capability of models pretrained with masked language modeling can be attributed to the semantic similarity encoded in the pretraining data’s distributional property. Via a synthetic dataset, our analysis suggests that distributional property indeed leads to the better sample efficiency of pretrained masked language models, but does not fully explain the generalization capability. We also conduct an analysis over two real-world datasets and demonstrate that the distributional property does not explain the generalization ability of pretrained natural language models either. Our results illustrate our limited understanding of model pretraining and provide future research directions.

pdf bib
Questions Are All You Need to Train a Dense Passage Retriever
Devendra Singh Sachan | Mike Lewis | Dani Yogatama | Luke Zettlemoyer | Joelle Pineau | Manzil Zaheer
Transactions of the Association for Computational Linguistics, Volume 11

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where state-of-the-art methods typically require large supervised datasets with custom hard-negative mining and denoising of positive examples. ART, in contrast, only requires access to unpaired inputs and outputs (e.g., questions and potential answer passages). It uses a new passage-retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evidence passages, and (2) the passages are then used to compute the probability of reconstructing the original question. Training for retrieval based on question reconstruction enables effective unsupervised learning of both passage and question encoders, which can be later incorporated into complete Open QA systems without any further finetuning. Extensive experiments demonstrate that ART obtains state-of-the-art results on multiple QA retrieval benchmarks with only generic initialization from a pre-trained language model, removing the need for labeled data and task-specific losses.1 Our code and model checkpoints are available at: https://github.com/DevSinghSachan/art.

2022

pdf bib
Relational Memory-Augmented Language Models
Qi Liu | Dani Yogatama | Phil Blunsom
Transactions of the Association for Computational Linguistics, Volume 10

We present a memory-augmented approach to condition an autoregressive language model on a knowledge graph. We represent the graph as a collection of relation triples and retrieve relevant relations for a given context to improve text generation. Experiments on WikiText-103, WMT19, and enwik8 English datasets demonstrate that our approach produces a better language model in terms of perplexity and bits per character. We also show that relational memory improves coherence, is complementary to token-based memory, and enables causal interventions. Our model provides a simple yet effective way to combine an autoregressive language model and a knowledge graph for more coherent and logical generation.

pdf bib
ABC: Attention with Bounded-memory Control
Hao Peng | Jungo Kasai | Nikolaos Pappas | Dani Yogatama | Zhaofeng Wu | Lingpeng Kong | Roy Schwartz | Noah A. Smith
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Transformer architectures have achieved state- of-the-art results on a variety of natural language processing (NLP) tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead prohibitive, especially for long sequences. Attention context can be seen as a random-access memory with each token taking a slot. Under this perspective, the memory size grows linearly with the sequence length, and so does the overhead of reading from it. One way to improve the efficiency is to bound the memory size. We show that disparate approaches can be subsumed into one abstraction, attention with bounded-memory control (ABC), and they vary in their organization of the memory. ABC reveals new, unexplored possibilities. First, it connects several efficient attention variants that would otherwise seem apart. Second, this abstraction gives new insights—an established approach (Wang et al., 2020b) previously thought to not be applicable in causal attention, actually is. Last, we present a new instance of ABC, which draws inspiration from existing ABC approaches, but replaces their heuristic memory-organizing functions with a learned, contextualized one. Our experiments on language modeling, machine translation, and masked language model finetuning show that our approach outperforms previous efficient attention models; compared to the strong transformer baselines, it significantly improves the inference time and space efficiency with no or negligible accuracy loss.

2021

pdf bib
Finetuning Pretrained Transformers into RNNs
Jungo Kasai | Hao Peng | Yizhe Zhang | Dani Yogatama | Gabriel Ilharco | Nikolaos Pappas | Yi Mao | Weizhu Chen | Noah A. Smith
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a signifi- cant computational cost, as the attention mechanism’s complexity scales quadratically with sequence length. Efficient transformer variants have received increasing interest in recent works. Among them, a linear-complexity recurrent variant has proven well suited for autoregressive generation. It approximates the softmax attention with randomized or heuristic feature maps, but can be difficult to train and may yield suboptimal accuracy. This work aims to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy. Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune. With a learned feature map, our approach provides an improved tradeoff between efficiency and accuracy over the standard transformer and other recurrent variants. We also show that the finetuning process has lower training cost relative to training these recurrent variants from scratch. As many models for natural language tasks are increasingly dependent on large-scale pretrained transformers, this work presents a viable approach to improving inference efficiency without repeating the expensive pretraining process.

pdf bib
Adaptive Semiparametric Language Models
Dani Yogatama | Cyprien de Masson d’Autume | Lingpeng Kong
Transactions of the Association for Computational Linguistics, Volume 9

We present a language model that combines a large parametric neural network (i.e., a transformer) with a non-parametric episodic memory component in an integrated architecture. Our model uses extended short-term context by caching local hidden states—similar to transformer-XL—and global long-term memory by retrieving a set of nearest neighbor tokens at each timestep. We design a gating function to adaptively combine multiple information sources to make a prediction. This mechanism allows the model to use either local context, short-term memory, or long-term memory (or any combination of them) on an ad hoc basis depending on the context. Experiments on word-based and character-based language modeling datasets demonstrate the efficacy of our proposed method compared to strong baselines.

2020

pdf bib
Syntactic Structure Distillation Pretraining for Bidirectional Encoders
Adhiguna Kuncoro | Lingpeng Kong | Daniel Fried | Dani Yogatama | Laura Rimell | Chris Dyer | Phil Blunsom
Transactions of the Association for Computational Linguistics, Volume 8

Textual representation learners trained on large amounts of data have achieved notable success on downstream tasks; intriguingly, they have also performed well on challenging tests of syntactic competence. Hence, it remains an open question whether scalable learners like BERT can become fully proficient in the syntax of natural language by virtue of data scale alone, or whether they still benefit from more explicit syntactic biases. To answer this question, we introduce a knowledge distillation strategy for injecting syntactic biases into BERT pretraining, by distilling the syntactically informative predictions of a hierarchical—albeit harder to scale—syntactic language model. Since BERT models masked words in bidirectional context, we propose to distill the approximate marginal distribution over words in context from the syntactic LM. Our approach reduces relative error by 2–21% on a diverse set of structured prediction tasks, although we obtain mixed results on the GLUE benchmark. Our findings demonstrate the benefits of syntactic biases, even for representation learners that exploit large amounts of data, and contribute to a better understanding of where syntactic biases are helpful in benchmarks of natural language understanding.

pdf bib
Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
Po-Sen Huang | Huan Zhang | Ray Jiang | Robert Stanforth | Johannes Welbl | Jack Rae | Vishal Maini | Dani Yogatama | Pushmeet Kohli
Findings of the Association for Computational Linguistics: EMNLP 2020

Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of generating coherent texts, it also prompts models to internalize social biases present in the training corpus. This paper aims to quantify and reduce a particular type of bias exhibited by language models: bias in the sentiment of generated text. Given a conditioning context (e.g., a writing prompt) and a language model, we analyze if (and how) the sentiment of the generated text is affected by changes in values of sensitive attributes (e.g., country names, occupations, genders) in the conditioning context using a form of counterfactual evaluation. We quantify sentiment bias by adopting individual and group fairness metrics from the fair machine learning literature, and demonstrate that large-scale models trained on two different corpora (news articles, and Wikipedia) exhibit considerable levels of bias. We then propose embedding and sentiment prediction-derived regularization on the language model’s latent representations. The regularizations improve fairness metrics while retaining comparable levels of perplexity and semantic similarity.

pdf bib
On the Cross-lingual Transferability of Monolingual Representations
Mikel Artetxe | Sebastian Ruder | Dani Yogatama
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

State-of-the-art unsupervised multilingual models (e.g., multilingual BERT) have been shown to generalize in a zero-shot cross-lingual setting. This generalization ability has been attributed to the use of a shared subword vocabulary and joint training across multiple languages giving rise to deep multilingual abstractions. We evaluate this hypothesis by designing an alternative approach that transfers a monolingual model to new languages at the lexical level. More concretely, we first train a transformer-based masked language model on one language, and transfer it to a new language by learning a new embedding matrix with the same masked language modeling objective, freezing parameters of all other layers. This approach does not rely on a shared vocabulary or joint training. However, we show that it is competitive with multilingual BERT on standard cross-lingual classification benchmarks and on a new Cross-lingual Question Answering Dataset (XQuAD). Our results contradict common beliefs of the basis of the generalization ability of multilingual models and suggest that deep monolingual models learn some abstractions that generalize across languages. We also release XQuAD as a more comprehensive cross-lingual benchmark, which comprises 240 paragraphs and 1190 question-answer pairs from SQuAD v1.1 translated into ten languages by professional translators.

pdf bib
A Call for More Rigor in Unsupervised Cross-lingual Learning
Mikel Artetxe | Sebastian Ruder | Dani Yogatama | Gorka Labaka | Eneko Agirre
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. An existing rationale for such research is based on the lack of parallel data for many of the world’s languages. However, we argue that a scenario without any parallel data and abundant monolingual data is unrealistic in practice. We also discuss different training signals that have been used in previous work, which depart from the pure unsupervised setting. We then describe common methodological issues in tuning and evaluation of unsupervised cross-lingual models and present best practices. Finally, we provide a unified outlook for different types of research in this area (i.e., cross-lingual word embeddings, deep multilingual pretraining, and unsupervised machine translation) and argue for comparable evaluation of these models.

2019

pdf bib
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Po-Sen Huang | Robert Stanforth | Johannes Welbl | Chris Dyer | Dani Yogatama | Sven Gowal | Krishnamurthy Dvijotham | Pushmeet Kohli
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such brittleness, but these are unlikely to find worst-case adversaries due to the complexity of the search space arising from discrete text perturbations. In this work, we approach the problem from the opposite direction: to formally verify a system’s robustness against a predefined class of adversarial attacks. We study text classification under synonym replacements or character flip perturbations. We propose modeling these input perturbations as a simplex and then using Interval Bound Propagation – a formal model verification method. We modify the conventional log-likelihood training objective to train models that can be efficiently verified, which would otherwise come with exponential search complexity. The resulting models show only little difference in terms of nominal accuracy, but have much improved verified accuracy under perturbations and come with an efficiently computable formal guarantee on worst case adversaries.

2018

pdf bib
LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better
Adhiguna Kuncoro | Chris Dyer | John Hale | Dani Yogatama | Stephen Clark | Phil Blunsom
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Language exhibits hierarchical structure, but recent work using a subject-verb agreement diagnostic argued that state-of-the-art language models, LSTMs, fail to learn long-range syntax sensitive dependencies. Using the same diagnostic, we show that, in fact, LSTMs do succeed in learning such dependencies—provided they have enough capacity. We then explore whether models that have access to explicit syntactic information learn agreement more effectively, and how the way in which this structural information is incorporated into the model impacts performance. We find that the mere presence of syntactic information does not improve accuracy, but when model architecture is determined by syntax, number agreement is improved. Further, we find that the choice of how syntactic structure is built affects how well number agreement is learned: top-down construction outperforms left-corner and bottom-up variants in capturing non-local structural dependencies.

2017

pdf bib
Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems
Wang Ling | Dani Yogatama | Chris Dyer | Phil Blunsom
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Solving algebraic word problems requires executing a series of arithmetic operations—a program—to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs.

2015

pdf bib
Extractive Summarization by Maximizing Semantic Volume
Dani Yogatama | Fei Liu | Noah A. Smith
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Bayesian Optimization of Text Representations
Dani Yogatama | Lingpeng Kong | Noah A. Smith
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Sparse Overcomplete Word Vector Representations
Manaal Faruqui | Yulia Tsvetkov | Dani Yogatama | Chris Dyer | Noah A. Smith
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
Embedding Methods for Fine Grained Entity Type Classification
Dani Yogatama | Daniel Gillick | Nevena Lazic
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)

2014

pdf bib
Linguistic Structured Sparsity in Text Categorization
Dani Yogatama | Noah A. Smith
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Dynamic Language Models for Streaming Text
Dani Yogatama | Chong Wang | Bryan R. Routledge | Noah A. Smith | Eric P. Xing
Transactions of the Association for Computational Linguistics, Volume 2

We present a probabilistic language model that captures temporal dynamics and conditions on arbitrary non-linguistic context features. These context features serve as important indicators of language changes that are otherwise difficult to capture using text data by itself. We learn our model in an efficient online fashion that is scalable for large, streaming data. With five streaming datasets from two different genres—economics news articles and social media—we evaluate our model on the task of sequential language modeling. Our model consistently outperforms competing models.

2012

pdf bib
A Probabilistic Model for Canonicalizing Named Entity Mentions
Dani Yogatama | Yanchuan Sim | Noah A. Smith
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

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
Predicting a Scientific Community’s Response to an Article
Dani Yogatama | Michael Heilman | Brendan O’Connor | Chris Dyer | Bryan R. Routledge | Noah A. Smith
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

2009

pdf bib
Multilingual Spectral Clustering Using Document Similarity Propagation
Dani Yogatama | Kumiko Tanaka-Ishii
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing