The paper presents a study on the portability of statistical syntactic knowledge in the framework of the structured language model (SLM). We investigate the impact of porting SLM statistics from the Wall Street Journal (WSJ) to the Air Travel Information System (ATIS) domain. We compare this approach to applying the Microsoft rule-based parser (NLPwin) for the ATIS data and to using a small amount of data manually parsed at UPenn for gathering the intial SLM statistics. Surprisingly, despite the fact that it performs modestly in perplexity (PPL), the model initialized on WSJ parses outperforms the other initialization methods based on in-domain annotated data, achieving a significant 0.4% absolute and 7% relative reduction in word error rate (WER) over a baseline system whose word error rate is 5.8%; the improvement measured relative to the minimum WER achievable on the N-best lists we worked with is 12%.
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；Mila（米拉计算科学研究所）；McGill University（麦吉尔大学）
It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic. In this paper, we make use of a multi-task objective, i.e., the models simultaneously predict words as well as ground truth parse trees in a form called "syntactic distances", where information between these two separate objectives shares the same intermediate representation. Experimental results on the Penn Treebank and Chinese Treebank datasets show that …
This paper evaluates global-scale dialect identification for 14 national varieties of English as a means for studying syntactic variation. The paper makes three main contributions: (i) introducing data-driven language mapping as a method for selecting the inventory of national varieties to include in the task; (ii) producing a large and dynamic set of syntactic features using grammar induction rather than focusing on a few hand-selected features such as function words; and (iii) comparing models across both web corpora and social media corpora in order to measure the robustness of syntactic va…
We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are implemented through a special attention mask and deterministic transformation of the linearized tree. We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics. Additionally, we find that the recursive syntactic composition bottleneck which repr…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs) are deep generative models that provide a probabilistic way to describe observations in the latent space. When applied to text data, the latent representations are often unstructured. We propose syntax-aware variational autoencoders (SAVAEs) that dedicate a subspace in the latent dimensions dubbed syntactic latent to represent syntactic structures of sentenc…
New York University（纽约大学）；Harvard University（哈佛大学）
Recent work using auxiliary prediction task classifiers to investigate the properties of LSTM representations has begun to shed light on why pretrained representations, like ELMo (Peters et al., 2018) and CoVe (McCann et al., 2017), are so beneficial for neural language understanding models. We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn. With this in mind, we compare four objectives---language modeling, translation, skip-thought, and autoencoding---on their ability to induce syntac…
Massachusetts Institute of Technology（麻省理工学院）；Harvard University（哈佛大学）
While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, existing work has not provided a clear picture about the model properties required to produce proper syntactic generalizations. We present a systematic evaluation of the syntactic knowledge of neural language models, testing 20 combinations of model types and data sizes on a set of 34 English-language syntactic test suites. We find substantia…
A Systematic Study of Compositional Syntactic Transformer Language Models
School of Information Science and Technology, ShanghaiTech University（信息科学与技术学院，上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（智能视觉与成像工程技术研究中心）；Ant Group（蚂蚁集团）
Exploring the Syntactic Abilities of RNNs with Multi-task Learning
PSL Research University（巴黎文理研究大学）；Bar Ilan University（巴伊兰大学）；CNRS（法国国家科学研究中心）；EHESS（法国社会科学高等研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
最近的工作已经探索了RNN的句法能力，使用主语-动词一致性任务，诊断对句子结构的敏感性。RNN在常见情况下很好地执行了这项任务，但在复杂句子中却表现不佳（Linzen et al.，2016年）。我们测试这些错误是否是由于固有的限制架构或相对间接的监督提供的大多数协议依赖于语料库。我们训练了一个RNN来执行协议任务和一个额外的任务，无论是CCG超级标记还是语言建模。多任务训练导致出错率显著降低，特别是在复杂句子上，这表明RNN有能力进化出比以前更复杂的句法表示。我们还表明，容易获得的协议训练数据可以提高其他语法任务的性能，特别是当只有有限的训练数据可用于这些任务。多任务范例还可以被利用来将语法知识注入到语言模型中。
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…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
We present PaLM, a hybrid parser and neural language model. Building on an RNN language model, PaLM adds an attention layer over text spans in the left context. An unsupervised constituency parser can be derived from its attention weights, using a greedy decoding algorithm. We evaluate PaLM on language modeling, and empirically show that it outperforms strong baselines. If syntactic annotations are available, the attention component can be trained in a supervised manner, providing syntactically-informed representations of the context, and further improving language modeling performance.
We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains. Recent theories have suggested that pretrained language models acquire useful inductive biases through masks that implicitly act as cloze reductions for downstream tasks. While appealing, we show that the success of the random masking strategy used in practice cannot be explained by such cloze-like masks alone. We construct cloze-like masks using task-specific lexicons for three different classification datasets and show that the majority of pretrained …
In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from Constraint Dependency Grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic dependency constraints. Two structured language models are applied for N-best rescoring, one is an almost-parsing language model, and the other utilizes more syntactic features by explicitly modeling syntactic dependencies between words…
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…
University of Mannheim（曼海姆大学）；University of Cambridge（剑桥大学）
Traditional NLP has long held (supervised) syntactic parsing necessary for successful higher-level semantic language understanding (LU). The recent advent of end-to-end neural models, self-supervised via language modeling (LM), and their success on a wide range of LU tasks, however, questions this belief. In this work, we empirically investigate the usefulness of supervised parsing for semantic LU in the context of LM-pretrained transformer networks. Relying on the established fine-tuning paradigm, we first couple a pretrained transformer with a biaffine parsing head, aiming to infuse explicit…
Recurrent Neural Networks (RNNs) trained on a language modeling task have been shown to acquire a number of non-local grammatical dependencies with some success. Here, we provide new evidence that RNN language models are sensitive to hierarchical syntactic structure by investigating the filler--gap dependency and constraints on it, known as syntactic islands. Previous work is inconclusive about whether RNNs learn to attenuate their expectations for gaps in island constructions in particular or in any sufficiently complex syntactic environment. This paper gives new evidence for the former by pr…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））
Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model's decision. We argue that current occlusion-based methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models. Furthermore, gradient-based explanation methods disregard the discrete…
GiLT: Augmenting Transformer Language Models with Dependency Graphs
School of Information Science and Technology, ShanghaiTech University（信息科学与技术学院，上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（智能视觉与成像上海工程研究中心）
The University of Tokyo（东京大学）；Artificial Intelligence Research Center, AIST（产业技术综合研究所人工智能研究中心）；LeapMind Inc.（LeapMind公司）
Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent tree-based LMs to the multilingual setting, where dependency treebanks are more common, is possible via dependency-to-constituency conversion methods. However, this raises the question of which tree formats are best for learning the model, and for which languages. We investigate this question by training recurrent neural network grammars (RNNGs) using various …
Facebook AI Research（Facebook人工智能研究院）；McGill University（麦吉尔大学）；Mila - Quebec AI（Mila - 魁北克人工智能研究所）
A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a different explanation: MLMs succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. To demonstrate this, we pre-train MLMs on sentences with randomly shuffled word order, and show that these models still achieve high accuracy after fine-tuning on many downstream tasks -- including on tasks specifically…
Compressive summarization systems typically rely on a crafted set of syntactic rules to determine what spans of possible summary sentences can be deleted, then learn a model of what to actually delete by optimizing for content selection (ROUGE). In this work, we propose to relax the rigid syntactic constraints on candidate spans and instead leave compression decisions to two data-driven criteria: plausibility and salience. Deleting a span is plausible if removing it maintains the grammaticality and factuality of a sentence, and spans are salient if they contain important information from the s…
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…
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…
An interesting and frequent type of multi-word expression (MWE) is the headless MWE, for which there are no true internal syntactic dominance relations; examples include many named entities ("Wells Fargo") and dates ("July 5, 2020") as well as certain productive constructions ("blow for blow", "day after day"). Despite their special status and prevalence, current dependency-annotation schemes require treating such flat structures as if they had internal syntactic heads, and most current parsers handle them in the same fashion as headed constructions. Meanwhile, outside the context of parsing, …
Word embeddings capture syntactic and semantic information about words. Definition modeling aims to make the semantic content in each embedding explicit, by outputting a natural language definition based on the embedding. However, existing definition models are limited in their ability to generate accurate definitions for different senses of the same word. In this paper, we introduce a new method that enables definition modeling for multiple senses. We show how a Gumble-Softmax approach outperforms baselines at matching sense-specific embeddings to definitions during training. In experiments, …
Today the pre-trained language models achieve great success for question generation (QG) task and significantly outperform traditional sequence-to-sequence approaches. However, the pre-trained models treat the input passage as a flat sequence and are thus not aware of the text structure of input passage. For QG task, we model text structure as answer position and syntactic dependency, and propose answer localness modeling and syntactic mask attention to address these limitations. Specially, we present localness modeling with a Gaussian bias to enable the model to focus on answer-surrounded con…
Yale University（耶鲁大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is effective, as the operation of the differentiable stack is not always interpretable. In this paper, we attempt to detect the presence of latent representations of hierarchical structure through an exploration of the unsupervised learning of constituency structure. Using a technique due to Shen et al. (2018a,b), we extract syntactic trees from the pushing behavior …
Tohoku University（东北大学）；Langsmith Inc.（朗史密斯公司）；University of Tokyo（东京大学）；RIKEN（理化学研究所）
Language models (LMs) have been used in cognitive modeling as well as engineering studies -- they compute information-theoretic complexity metrics that simulate humans' cognitive load during reading. This study highlights a limitation of modern neural LMs as the model of choice for this purpose: there is a discrepancy between their context access capacities and that of humans. Our results showed that constraining the LMs' context access improved their simulation of human reading behavior. We also showed that LM-human gaps in context access were associated with specific syntactic constructions;…
Slot filling and intent detection are two fundamental tasks in the field of natural language understanding. Due to the strong correlation between these two tasks, previous studies make efforts on modeling them with multi-task learning or designing feature interaction modules to improve the performance of each task. However, none of the existing approaches consider the relevance between the structural information of sentences and the label semantics of two tasks. The intent and semantic components of a utterance are dependent on the syntactic elements of a sentence. In this paper, we investigat…
With a growing interest in modeling inherent subjectivity in natural language, we present a linguistically-motivated process to understand and analyze the writing style of individuals from three perspectives: lexical, syntactic, and semantic. We discuss the stylistically expressive elements within each of these levels and use existing methods to quantify the linguistic intuitions related to some of these elements. We show that such a multi-level analysis is useful for developing a well-knit understanding of style - which is independent of the natural language task at hand, and also demonstrate…
