A modular design encourages neural models to disentangle and recombine different facets of knowledge to generalise more systematically to new tasks. In this work, we assume that each task is associated with a subset of latent skills from an (arbitrary size) inventory. In turn, each skill corresponds to a parameter-efficient (sparse / low-rank) model adapter. By jointly learning adapters and a routing function that allocates skills to each task, the full network is instantiated as the average of the parameters of active skills. We propose several inductive biases that encourage re-usage and composition of the skills, including variable-size skill allocation and a dual-speed learning rate. We evaluate our latent-skill model in two main settings: 1) multitask reinforcement learning for instruction following on 8 levels of the BabyAI platform; and 2) few-shot fine-tuning of language models on 160 NLP tasks of the CrossFit benchmark. We find that the modular design of our network enhances sample efficiency in reinforcement learning and few-shot generalisation in supervised learning, compared to a series of baselines. These include models where parameters are fully shared, task-specific, conditionally generated (HyperFormer), or sparse mixture-of-experts (TaskMoE).

Morphological systems across languages vary when it comes to the relation between form and meaning. In some languages, a single meaning feature corresponds to a single morpheme, whereas in other languages, multiple meaning features are bundled together into one morpheme. The two types of languages have been called agglutinative and fusional, respectively, but this distinction does not capture the graded nature of the phenomenon. We provide a mathematically precise way of characterizing morphological systems using partial information decomposition, a framework for decomposing mutual information into three components: unique, redundant, and synergistic information. We show that highly fusional languages are characterized by high levels of synergy.

Class-based language models (LMs) have been long devised to address context sparsity in n-gram LMs. In this study, we revisit this approach in the context of neural LMs. We hypothesize that class-based prediction leads to an implicit context aggregation for similar words and thus can improve generalization for rare words. We map words that have a common WordNet hypernym to the same class and train large neural LMs by gradually annealing from predicting the class to token prediction during training. Empirically, this curriculum learning strategy consistently improves perplexity over various large, highly-performant state-of-the-art Transformer-based models on two datasets, WikiText-103 and ARXIV. Our analysis shows that the performance improvement is achieved without sacrificing performance on rare words. Finally, we document other attempts that failed to yield empirical gains, and discuss future directions for the adoption of class-based LMs on a larger scale.

Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.

Transformer models pre-trained with a masked-language-modeling objective (e.g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the semantics of the pre-training corpora is an open question. To answer this question, we selectively inject verbalized knowledge into the pre-training minibatches of BERT and evaluate how well the model generalizes to supported inferences after pre-training on the injected knowledge. We find generalization does not improve over the course of pre-training BERT from scratch, suggesting that commonsense knowledge is acquired from surface-level, co-occurrence patterns rather than induced, systematic reasoning.

Pretrained large generative language models have shown great performance on many tasks, but exhibit low compositional generalization abilities. Scaling such models has been shown to improve their performance on various NLP tasks even just by conditioning them on a few examples to solve the task without any fine-tuning (also known as in-context learning). In this work, we look at the gap between the in-distribution (ID) and out-of-distribution (OOD) performance of such models in semantic parsing tasks with in-context learning. In the ID settings, the demonstrations are from the same split (test or train) that the model is being evaluated on, and in the OOD settings, they are from the other split. We look at how the relative generalization gap of in-context learning evolves as models are scaled up. We evaluate four model families, OPT, BLOOM, CodeGen and Codex on three semantic parsing datasets, CFQ, SCAN and GeoQuery with different number of exemplars, and observe a trend of decreasing relative generalization gap as models are scaled up.

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus. By training BERT with the resulting combined objective we reduce the mean top 1 error rate to 4% on the negated LAMA dataset. We also see some improvements on the negated NLI benchmarks.

Syntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization problems and over-parametrization. In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM). The model explicitly models the structure with an incremental parser and maintains the conditional probability setting of a standard language model (left-to-right). To train the incremental parser and avoid exposure bias, we also propose a novel dynamic oracle, so that SOM is more robust to wrong parsing decisions. Experiments show that SOM can achieve strong results in language modeling, incremental parsing, and syntactic generalization tests while using fewer parameters than other models.

By the age of two, children tend to assume that new word categories are based on objects’ shape, rather than their color or texture; this assumption is called the shape bias. They are thought to learn this bias by observing that their caregiver’s language is biased towards shape based categories. This presents a chicken and egg problem: if the shape bias must be present in the language in order for children to learn it, how did it arise in language in the first place? In this paper, we propose that communicative efficiency explains both how the shape bias emerged and why it persists across generations. We model this process with neural emergent language agents that learn to communicate about raw pixelated images. First, we show that the shape bias emerges as a result of efficient communication strategies employed by agents. Second, we show that pressure brought on by communicative need is also necessary for it to persist across generations; simply having a shape bias in an agent’s input language is insufficient. These results suggest that, over and above the operation of other learning strategies, the shape bias in human learners may emerge and be sustained by communicative pressures.

Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the majority of data points, have been shown to increase the out-of-distribution generalization of pre-trained language models. In this paper, we first propose using example forgetting to find minority examples without prior knowledge of the spurious correlations present in the dataset. Forgettable examples are instances either learned and then forgotten during training or never learned. We show empirically how these examples are related to minorities in our training sets. Then, we introduce a new approach to robustify models by fine-tuning our models twice, first on the full training data and second on the minorities only. We obtain substantial improvements in out-of-distribution generalization when applying our approach to the MNLI, QQP and FEVER datasets.

Are pairs of words that tend to occur together also likely to stand in a linguistic dependency? This empirical question is motivated by a long history of literature in cognitive science, psycholinguistics, and NLP. In this work we contribute an extensive analysis of the relationship between linguistic dependencies and statistical dependence between words. Improving on previous work, we introduce the use of large pretrained language models to compute contextualized estimates of the pointwise mutual information between words (CPMI). For multiple models and languages, we extract dependency trees which maximize CPMI, and compare to gold standard linguistic dependencies. Overall, we find that CPMI dependencies achieve an unlabelled undirected attachment score of at most ≈ 0.5. While far above chance, and consistently above a non-contextualized PMI baseline, this score is generally comparable to a simple baseline formed by connecting adjacent words. We analyze which kinds of linguistic dependencies are best captured in CPMI dependencies, and also find marked differences between the estimates of the large pretrained language models, illustrating how their different training schemes affect the type of dependencies they capture.

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing neural predictions by highlighting salient concepts in the text as justifications or rationales, they rely on thousands of labeled training examples for both task labels as well as annotated rationales for every instance. Such extensive large-scale annotations are infeasible to obtain for many tasks. To this end, we develop a multi-task teacher-student framework based on self-training pre-trained language models with limited task-specific labels and rationales and judicious sample selection to learn from informative pseudo-labeled examples. We study several characteristics of what constitutes a good rationale and demonstrate that the neural model performance can be significantly improved by making it aware of its rationalized predictions, particularly in low-resource settings. Extensive experiments in several benchmark datasets demonstrate the effectiveness of our approach.

Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this paper, we conduct an extensive study of the transferability between 33 NLP tasks across three broad classes of problems (text classification, question answering, and sequence labeling). Our results show that transfer learning is more beneficial than previously thought, especially when target task data is scarce, and can improve performance even with low-data source tasks that differ substantially from the target task (e.g., part-of-speech tagging transfers well to the DROP QA dataset). We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size. Overall, our experiments reveal that factors such as data size, task and domain similarity, and task complexity all play a role in determining transferability.

We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN, where it outperforms previous models on the LENGTH split, and English question formation, where it performs comparably to decoders with the ground-truth tree structure. We also present experimental results on German-English translation on the Multi30k dataset, and qualitatively analyse the induced tree structures our model learns for the SCAN tasks and the German-English translation task.

We propose a hierarchical model for sequential data that learns a tree on-the-fly, i.e. while reading the sequence. In the model, a recurrent network adapts its structure and reuses recurrent weights in a recursive manner. This creates adaptive skip-connections that ease the learning of long-term dependencies. The tree structure can either be inferred without supervision through reinforcement learning, or learned in a supervised manner. We provide preliminary experiments in a novel Math Expression Evaluation (MEE) task, which is created to have a hierarchical tree structure that can be used to study the effectiveness of our model. Additionally, we test our model in a well-known propositional logic and language modelling tasks. Experimental results have shown the potential of our approach.

In this work, we propose a novel constituency parsing scheme. The model first predicts a real-valued scalar, named syntactic distance, for each split position in the sentence. The topology of grammar tree is then determined by the values of syntactic distances. Compared to traditional shift-reduce parsing schemes, our approach is free from the potentially disastrous compounding error. It is also easier to parallelize and much faster. Our model achieves the state-of-the-art single model F1 score of 92.1 on PTB and 86.4 on CTB dataset, which surpasses the previous single model results by a large margin.

We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.

We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text in the articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. Analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (13.3% F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available online.