Sun Yat-sen University（中山大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Search Technology Center Asia（微软亚洲搜索技术中心）
Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Nan Duan, Daxin Jiang
备注：
Accepted by ACL-IJCNLP 2021: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens.
As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence. This paper investigates how to incorporate syntactic knowledge into the SRL task effectively. We present different approaches of encoding the syntactic information derived from dependency trees of different quality and representations; we propose a syntax-enhanced self-attention model and compare it with other two strong baseline methods; and we conduct experiments with newly published deep contextualized word representations as well. The experiment results demons…
Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and Tree-Linearization methods, which may suffer from error propagation. In this work, we propose a novel method to integrate source-side syntax implicitly for NMT. The basic idea is to use the intermediate hidden representations of a well-trained end-to-end dependency parser, which are referred to as syntax-aware word representations (SAWRs). Then, we simply concatenate …
This work proposes a syntax-enhanced grammatical error correction (GEC) approach named SynGEC that effectively incorporates dependency syntactic information into the encoder part of GEC models. The key challenge for this idea is that off-the-shelf parsers are unreliable when processing ungrammatical sentences. To confront this challenge, we propose to build a tailored GEC-oriented parser (GOPar) using parallel GEC training data as a pivot. First, we design an extended syntax representation scheme that allows us to represent both grammatical errors and syntax in a unified tree structure. Then, …
Recent studies on Knowledge Base Question Answering (KBQA) have shown great progress on this task via better question understanding. Previous works for encoding questions mainly focus on the word sequences, but seldom consider the information from syntactic trees.In this paper, we propose an approach to learn syntax-based representations for KBQA. First, we encode path-based syntax by considering the shortest dependency paths between keywords. Then, we propose two encoding strategies to mode the information of whole syntactic trees to obtain tree-based syntax. Finally, we combine both path-bas…
Latent Semantic Analysis (LSA) is a widely used Information Retrieval method based on "bag-of-words" assumption. However, according to general conception, syntax plays a role in representing meaning of sentences. Thus, enhancing LSA with part-of-speech (POS) information to capture the context of word occurrences appears to be theoretically feasible extension. The approach is tested empirically on a automatic essay grading system using LSA for document similarity comparisons. A comparison on several POS-enhanced LSA models is reported. Our findings show that the addition of contextual informati…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；School of Computer Science, McGill University（麦吉尔大学计算机学院）；Stanford University（斯坦福大学）
Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency tree information into pre-trained transformer models (e.g., BERT) remains unclear, especially given recent studies highlighting how these models implicitly encode syntax. In this work, we systematically study the utility of incorporating dependency trees into pre-trained transformers on three representative information extraction tasks: semantic role labeling (SRL), named entity recognition, and relation extraction. …
For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanism for better linguistically motivated word representations. In detail, for self-attention network (SAN)…
College of Information and Computer Sciences（信息与计算机科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Dependency parsing research, which has made significant gains in recent years, typically focuses on improving the accuracy of single-tree predictions. However, ambiguity is inherent to natural language syntax, and communicating such ambiguity is important for error analysis and better-informed downstream applications. In this work, we propose a transition sampling algorithm to sample from the full joint distribution of parse trees defined by a transition-based parsing model, and demonstrate the use of the samples in probabilistic dependency analysis. First, we define the new task of dependency…
Recently, semantic role labeling (SRL) has earned a series of success with even higher performance improvements, which can be mainly attributed to syntactic integration and enhanced word representation. However, most of these efforts focus on English, while SRL on multiple languages more than English has received relatively little attention so that is kept underdevelopment. Thus this paper intends to fill the gap on multilingual SRL with special focus on the impact of syntax and contextualized word representation. Unlike existing work, we propose a novel method guided by syntactic rule to prun…
University of Science and Technology of China（中国科学技术大学）
Sentence semantic understanding is a key topic in the field of natural language processing. Recently, contextualized word representations derived from pre-trained language models such as ELMO and BERT have shown significant improvements for a wide range of semantic tasks, e.g. question answering, text classification and sentiment analysis. However, how to add external knowledge to further improve the semantic modeling capability of model is worth probing. In this paper, we propose a novel approach to combining syntax information with a pre-trained language model. In order to evaluate the effec…
Extracting temporal relations (e.g., before, after, and simultaneous) among events is crucial to natural language understanding. One of the key challenges of this problem is that when the events of interest are far away in text, the context in-between often becomes complicated, making it challenging to resolve the temporal relationship between them. This paper thus proposes a new Syntax-guided Graph Transformer network (SGT) to mitigate this issue, by (1) explicitly exploiting the connection between two events based on their dependency parsing trees, and (2) automatically locating temporal cue…
In low resource settings, data augmentation strategies are commonly leveraged to improve performance. Numerous approaches have attempted document-level augmentation (e.g., text classification), but few studies have explored token-level augmentation. Performed naively, data augmentation can produce semantically incongruent and ungrammatical examples. In this work, we compare simple masked language model replacement and an augmentation method using constituency tree mutations to improve the performance of named entity recognition in low-resource settings with the aim of preserving linguistic coh…
This thesis is concerned with type-logical grammars and their practical applicability as tools of reasoning about sentence syntax and semantics. The focal point is narrowed to Dutch, a language exhibiting a large degree of word order variability. In order to overcome difficulties arising as a result of that variability, the thesis explores and expands upon a type grammar based on Multiplicative Intuitionistic Linear Logic, agnostic to word order but enriched with decorations that aim to reduce its proof-theoretic complexity. An algorithm for the conversion of dependency-annotated sentences int…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP applications. However, how to incorporate the syntax trees effectively and efficiently into pre-trained Transformers is still unsettled. In this paper, we address this problem by proposing a novel framework named Syntax-BERT. This framework works in a plug-and-play mode and is applicable to an arbitrary pre-trained checkpoint based on Transformer architecture. Exper…
Existing text style transfer (TST) methods rely on style classifiers to disentangle the text's content and style attributes for text style transfer. While the style classifier plays a critical role in existing TST methods, there is no known investigation on its effect on the TST methods. In this paper, we conduct an empirical study on the limitations of the style classifiers used in existing TST methods. We demonstrate that the existing style classifiers cannot learn sentence syntax effectively and ultimately worsen existing TST models' performance. To address this issue, we propose a novel Sy…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Carnegie Mellon University（卡内基梅隆大学）；Google DeepMind（谷歌DeepMind）；University of Washington（华盛顿大学）
Shallow syntax provides an approximation of phrase-syntactic structure of sentences; it can be produced with high accuracy, and is computationally cheap to obtain. We investigate the role of shallow syntax-aware representations for NLP tasks using two techniques. First, we enhance the ELMo architecture to allow pretraining on predicted shallow syntactic parses, instead of just raw text, so that contextual embeddings make use of shallow syntactic context. Our second method involves shallow syntactic features obtained automatically on downstream task data. Neither approach leads to a significant…
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive useful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings o…
Japan Science and Technology Agency（日本科学技术振兴机构）；Graduate School of Informatics, Kyoto University（京都大学信息学研究科）
As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser. Previous studies formalize it as a string-to-string problem and solve it in an unsupervised way, which suffers from data sparseness due to the small size of training data for English-AMR alignment. In this paper, we formalize it as a syntax-based alignment problem and solve it in a supervised manner based on syntax trees, which can address the data sparseness problem by generalizing English-AMR t…
University of Washington（华盛顿大学）；Paul G. Allen School of Computer Science & Engineering（保罗·G·艾伦计算机科学与工程学院）
We present a set of experiments to demonstrate that deep recurrent neural networks (RNNs) learn internal representations that capture soft hierarchical notions of syntax from highly varied supervision. We consider four syntax tasks at different depths of the parse tree; for each word, we predict its part of speech as well as the first (parent), second (grandparent) and third level (great-grandparent) constituent labels that appear above it. These predictions are made from representations produced at different depths in networks that are pretrained with one of four objectives: dependency parsin…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Facebook AI（脸书人工智能研究院）
In recent years, we have seen a colossal effort in pre-training multilingual text encoders using large-scale corpora in many languages to facilitate cross-lingual transfer learning. However, due to typological differences across languages, the cross-lingual transfer is challenging. Nevertheless, language syntax, e.g., syntactic dependencies, can bridge the typological gap. Previous works have shown that pre-trained multilingual encoders, such as mBERT \cite{devlin-etal-2019-bert}, capture language syntax, helping cross-lingual transfer. This work shows that explicitly providing language syntax…
Wuhan University（武汉大学）；Guangdong University of Foreign Studies（广东外语外贸大学）
In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating rich syntactic knowledge. We first build a syntax fusion encoder for encoding syntactic features, including a label-aware graph convolutional network (LAGCN) for modeling the dependency edges and labels, as well as the POS tags unifiedly, and a local-attention module encoding POS tags for better term boundary detection. During pairing, we then adopt Biaffine and Triaffine scoring for high-order aspect-opinion term pairing, in the meantime re-harnessing the syntax-enriched repres…
Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained lan…
Semantic role labeling (SRL), also known as shallow semantic parsing, is an important yet challenging task in NLP. Motivated by the close correlation between syntactic and semantic structures, traditional discrete-feature-based SRL approaches make heavy use of syntactic features. In contrast, deep-neural-network-based approaches usually encode the input sentence as a word sequence without considering the syntactic structures. In this work, we investigate several previous approaches for encoding syntactic trees, and make a thorough study on whether extra syntax-aware representations are benefic…
Neural networks trained on natural language processing tasks capture syntax even though it is not provided as a supervision signal. This indicates that syntactic analysis is essential to the understating of language in artificial intelligence systems. This overview paper covers approaches of evaluating the amount of syntactic information included in the representations of words for different neural network architectures. We mainly summarize re-search on English monolingual data on language modeling tasks and multilingual data for neural machine translation systems and multilingual language mod…
As the name suggests, type-logical grammars are a grammar formalism based on logic and type theory. From the prespective of grammar design, type-logical grammars develop the syntactic and semantic aspects of linguistic phenomena hand-in-hand, letting the desired semantics of an expression inform the syntactic type and vice versa. Prototypical examples of the successful application of type-logical grammars to the syntax-semantics interface include coordination, quantifier scope and extraction.This chapter describes the Grail theorem prover, a series of tools for designing and testing grammars i…
Grammatical Error Correction (GEC) is a task of detecting and correcting grammatical errors in sentences. Recently, neural machine translation systems have become popular approaches for this task. However, these methods lack the use of syntactic knowledge which plays an important role in the correction of grammatical errors. In this work, we propose a syntax-guided GEC model (SG-GEC) which adopts the graph attention mechanism to utilize the syntactic knowledge of dependency trees. Considering the dependency trees of the grammatically incorrect source sentences might provide incorrect syntactic…
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）
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 also investigate the effect of moving from bag-of-words to recurrent neural network modules. We evaluate our models as well as several popular pretrained embeddings on standard semantic similarity tasks a…
University of Maryland, College Park（马里兰大学帕克分校）；Google Research（谷歌研究院）；Washington University in St. Louis（圣路易斯华盛顿大学）；University of California, Berkeley（加州大学伯克利分校）
Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence without explicitly modeling its structure. Some prior works show that pre-trained language models can capture the syntactic rules of natural languages without finetuning on syntax understanding tasks. However, there is limited understanding of how well pre-trained models understand the code structure so far. In this work, we perform the first thorough benchmarking of the state-of-the-art pre-trained models for identify…
Pregroup grammars were developed in 1999 and stayed Lambek's preferred algebraic model of grammar. The set-theoretic semantics of pregroups, however, faces an ambiguity problem. In his latest book, Lambek suggests that this problem might be overcome using finite dimensional vector spaces rather than sets. What is the right notion of composition in this setting, direct sum or tensor product of spaces?
Alibaba Group（阿里巴巴集团）；University of Chinese Academy of Sciences（中国科学院大学）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing. The state-of-the-art graph-based encoder has been successfully used in this task but does not model the question syntax well. In this paper, we propose S$^2$SQL, injecting Syntax to question-Schema graph encoder for Text-to-SQL parsers, which effectively leverages the syntactic dependency information of questions in text-to-SQL to improve the performance. We also employ the decoupling constraint to induce diverse relational edge embedding, which fur…
University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）
We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation. We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data. Our GCNs use predicted syntactic dependency trees of source sentences to produce representations of words (i.e. hidden states of the encoder) that are sensitive to their syntactic neighborhoods. GCNs take word representations as input and produce word representations as output, so they can easily be incorporated as…
Most existing studies in text-to-SQL tasks do not require generating complex SQL queries with multiple clauses or sub-queries, and generalizing to new, unseen databases. In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and cross-domain text-to-SQL generation task. SyntaxSQLNet employs a SQL specific syntax tree-based decoder with SQL generation path history and table-aware column attention encoders. We evaluate SyntaxSQLNet on the Spider text-to-SQL task, which contains databases with multiple tables and complex SQL queries with multiple SQL clauses and neste…
LMU Munich（慕尼黑大学）；Munich Center of Machine Learning（慕尼黑机器学习中心）；University of Oxford（牛津大学）
Construction Grammar (CxG) is a paradigm from cognitive linguistics emphasising the connection between syntax and semantics. Rather than rules that operate on lexical items, it posits constructions as the central building blocks of language, i.e., linguistic units of different granularity that combine syntax and semantics. As a first step towards assessing the compatibility of CxG with the syntactic and semantic knowledge demonstrated by state-of-the-art pretrained language models (PLMs), we present an investigation of their capability to classify and understand one of the most commonly studie…
Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models may use representations of syntax, but probes may have learned to use redundant encodings of the same syntactic information. We demonstrate that models do encode syntactic information redundantly and introduce a new probe design that guides probes to consider all syntactic information present in embeddings. Using these probes, we find evidence for the use of syntax in models where prior methods did not, allowing us …
UBTECH Sydney AI Centre（优必选悉尼人工智能中心）；University of Sydney（悉尼大学）
Syntax-incorporated machine translation models have been proven successful in improving the model's reasoning and meaning preservation ability. In this paper, we propose a simple yet effective graph-structured encoder, the Recurrent Graph Syntax Encoder, dubbed \textbf{RGSE}, which enhances the ability to capture useful syntactic information. The RGSE is done over a standard encoder (recurrent or self-attention encoder), regarding recurrent network units as graph nodes and injects syntactic dependencies as edges, such that RGSE models syntactic dependencies and sequential information (\textit{…
Mila（米拉）；Université de Montréal（蒙特利尔大学）；Microsoft Research Montréal（微软蒙特利尔研究院）；McGill University（麦吉尔大学）
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 sho…
Notwithstanding recent advances, syntactic generalization remains a challenge for text decoders. While some studies showed gains from incorporating source-side symbolic syntactic and semantic structure into text generation Transformers, very little work addressed the decoding of such structure. We propose a general approach for tree decoding using a transition-based approach. Examining the challenging test case of incorporating Universal Dependencies syntax into machine translation, we present substantial improvements on test sets that focus on syntactic generalization, while presenting improv…
Institute of Mathematical and Computer Sciences, University of São Paulo（圣保罗大学数学与计算机科学研究所）
A minimal constructed language (conlang) is useful for experiments and comfortable for making tools. The Toki Pona (TP) conlang is minimal both in the vocabulary (with only 14 letters and 124 lemmas) and in the (about) 10 syntax rules. The language is useful for being a used and somewhat established minimal conlang with at least hundreds of fluent speakers. This article exposes current concepts and resources for TP, and makes available Python (and Vim) scripted routines for the analysis of the language, synthesis of texts, syntax highlighting schemes, and the achievement of a preliminary TP Wo…
University of Cambridge（剑桥大学）；ETH Zürich（苏黎世联邦理工学院）
Analysing whether neural language models encode linguistic information has become popular in NLP. One method of doing so, which is frequently cited to support the claim that models like BERT encode syntax, is called probing; probes are small supervised models trained to extract linguistic information from another model's output. If a probe is able to predict a particular structure, it is argued that the model whose output it is trained on must have implicitly learnt to encode it. However, drawing a generalisation about a model's linguistic knowledge about a specific phenomena based on what a p…
We describe an efficient bottom-up parser that interleaves syntactic and semantic structure building. Two techniques are presented for reducing search by reducing local ambiguity: Limited left-context constraints are used to reduce local syntactic ambiguity, and deferred sortal-constraint application is used to reduce local semantic ambiguity. We experimentally evaluate these techniques, and show dramatic reductions in both number of chart-edges and total parsing time. The robust processing capabilities of the parser are demonstrated in its use in improving the accuracy of a speech recognizer.
University of Amsterdam（阿姆斯特丹大学）；Yandex；University of Edinburgh（爱丁堡大学）
We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler achieves competitive performance on English, even without any kind of syntactic information and only using local inference. However, when automatically predicted part-of-speech tags are provided as input, it substantially outperforms all previous local models and approaches the best reported results on the English CoNLL-2009 dataset. We also consider Chinese, Czech and Spanish…
$\mathcal{S}^2$IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
School of Computer Science, Guangdong University of Technology（广东技术大学计算机科学学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东人工智能与数字经济实验室（深圳））；Peng Cheng Laboratory（鹏城实验室）；College of Science, Shantou University（汕头大学理学院）
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two separate latent spaces, for sentences and syntactic trees. The evidence lower bound objective is redesigned correspondingly, by optimizing a joint distribution that accommodates two encoders and two decoders. SIVAE works with long short-term memory architectures to simultaneously generate sentences and syntactic trees. Two versions of SIVAE are proposed: one ca…
