Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained on utterance-denotation pairs treating programs as latent. The task is challenging due to the large search space and spuriousness of programs which may execute to the correct answer but do not generalize to unseen examples. Our goal is to instill an inductive bias in the parser to help it distinguish between spurious and correct programs. We capitalize on the intuition that correct programs would likely respect certain structural constraints were they to be aligned to the question (e.g., program fragments are unlikely to align to overlapping text spans) and propose to model alignments as structured latent variables. In order to make the latent-alignment framework tractable, we decompose the parsing task into (1) predicting a partial "abstract program" and (2) refining it while modeling structured alignments with differential dynamic programming. We obtain state-of-the-art performance on the WIKITABLEQUESTIONS and WIKISQL datasets. When compared to a standard attention baseline, we observe that the proposed structured-alignment mechanism is highly beneficial.
Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e.g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions. This contrasts with earlier work and also with the intuition that the labels of individual arguments are strongly interdependent. We model interactions between argument labeling decisions through {\it iterative refinement}. Starting with an output produced by a factorized model, we iteratively refine it using a refinement network. Instead of modeling arbitrary interactions among roles and words, we encode prior knowledge about the SRL problem by designing a restricted network architecture capturing non-local interactions. This modeling choice prevents overfitting and results in an effective model, outperforming strong factorized baseline models on all 7 CoNLL-2009 languages, and achieving state-of-the-art results on 5 of them, including English.
Modern sentence-level NMT systems often produce plausible translations of isolated sentences. However, when put in context, these translations may end up being inconsistent with each other. We propose a monolingual DocRepair model to correct inconsistencies between sentence-level translations. DocRepair performs automatic post-editing on a sequence of sentence-level translations, refining translations of sentences in context of each other. For training, the DocRepair model requires only monolingual document-level data in the target language. It is trained as a monolingual sequence-to-sequence model that maps inconsistent groups of sentences into consistent ones. The consistent groups come from the original training data; the inconsistent groups are obtained by sampling round-trip translations for each isolated sentence. We show that this approach successfully imitates inconsistencies we aim to fix: using contrastive evaluation, we show large improvements in the translation of several contextual phenomena in an English-Russian translation task, as well as improvements in the BLEU score. We also conduct a human evaluation and show a strong preference of the annotators to corrected translations over the baseline ones. Moreover, we analyze which discourse phenomena are hard to capture using monolingual data only.
We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our analysis as they have been shown effective on various tasks, including machine translation (MT), standard left-to-right language models (LM) and masked language modeling (MLM). Previous work used black-box probing tasks to show that the representations learned by the Transformer differ significantly depending on the objective. In this work, we use canonical correlation analysis and mutual information estimators to study how information flows across Transformer layers and how this process depends on the choice of learning objective. For example, as you go from bottom to top layers, information about the past in left-to-right language models gets vanished and predictions about the future get formed. In contrast, for MLM, representations initially acquire information about the context around the token, partially forgetting the token identity and producing a more generalized token representation. The token identity then gets recreated at the top MLM layers.
The general trend in NLP is towards increasing model capacity and performance via deeper neural networks. However, simply stacking more layers of the popular Transformer architecture for machine translation results in poor convergence and high computational overhead. Our empirical analysis suggests that convergence is poor due to gradient vanishing caused by the interaction between residual connections and layer normalization. We propose depth-scaled initialization (DS-Init), which decreases parameter variance at the initialization stage, and reduces output variance of residual connections so as to ease gradient back-propagation through normalization layers. To address computational cost, we propose a merged attention sublayer (MAtt) which combines a simplified averagebased self-attention sublayer and the encoderdecoder attention sublayer on the decoder side. Results on WMT and IWSLT translation tasks with five translation directions show that deep Transformers with DS-Init and MAtt can substantially outperform their base counterpart in terms of BLEU (+1.1 BLEU on average for 12-layer models), while matching the decoding speed of the baseline model thanks to the efficiency improvements of MAtt.
The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and propagated through a deep network of hidden layers. We argue that the need to represent and propagate lexical features in each layer limits the model's capacity for learning and representing other information relevant to the task. To alleviate this bottleneck, we introduce gated shortcut connections between the embedding layer and each subsequent layer within the encoder and decoder. This enables the model to access relevant lexical content dynamically, without expending limited resources on storing it within intermediate states. We show that the proposed modification yields consistent improvements over a baseline transformer on standard WMT translation tasks in 5 translation directions (0.9 BLEU on average) and reduces the amount of lexical information passed along the hidden layers. We furthermore evaluate different ways to integrate lexical connections into the transformer architecture and present ablation experiments exploring the effect of proposed shortcuts on model behavior.
We treat projective dependency trees as latent variables in our probabilistic model and induce them in such a way as to be beneficial for a downstream task, without relying on any direct tree supervision. Our approach relies on Gumbel perturbations and differentiable dynamic programming. Unlike previous approaches to latent tree learning, we stochastically sample global structures and our parser is fully differentiable. We illustrate its effectiveness on sentiment analysis and natural language inference tasks. We also study its properties on a synthetic structure induction task. Ablation studies emphasize the importance of both stochasticity and constraining latent structures to be projective trees.
Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance of the model and analyze the roles played by them. We find that the most important and confident heads play consistent and often linguistically-interpretable roles. When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, we observe that specialized heads are last to be pruned. Our novel pruning method removes the vast majority of heads without seriously affecting performance. For example, on the English-Russian WMT dataset, pruning 38 out of 48 encoder heads results in a drop of only 0.15 BLEU.
Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts, learns to choose entities relying both on local context of each mention and on coherence with other entities in the document. The resulting approach rivals fully-supervised state-of-the-art systems on standard test sets. It also approaches their performance in the very challenging setting: when tested on a test set sampled from the data used to estimate the supervised systems. By comparing to Wikipedia-only training of our model, we demonstrate that modeling unlabeled documents is beneficial.
Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels. As the learning signal is weak and our surrogate labels are noisy, we introduce a noise detection component in our model: it lets the model detect and disregard examples which are likely to be noisy. Our method, jointly learning to detect noise and link entities, greatly outperforms the surface matching baseline. For a subset of entity categories, it even approaches the performance of supervised learning.