Unsupervised Grammar Induction with Depth-bounded PCFG
The Ohio State University（俄亥俄州立大学）；Harvard University（哈佛大学）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz
备注：
Accepted by Transactions of the Association for Computational Linguistics
There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchical sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech and newswire text exceed or are competitive with those of other models when evaluated on parse accuracy. Moreover, gram- mars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.
Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Edinburgh（爱丁堡大学）；University of Chinese Academy of Sciences（中国科学院大学）
Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG representation and parsing, previous approaches cannot scale up to a relatively large number of (nonterminal and preterminal) symbols. In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols. We further use neu…
Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程研究中心）；ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Edinburgh（爱丁堡大学）；University of Chinese Academy of Sciences（中国科学院大学）
Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction. However, to reduce computational complexity, they make a strong independence assumption on the generation of the child word and thus bilexical dependencies are ignored. In this paper, we propose an approach to parameterize L-PCFGs without making implausible independence assumptions. Our approach directly models bilexical dependencies and meanwhile reduces both learning and representation complexities of L-PCFGs. Experimental results on the English WSJ dataset confirm the effectiveness of our approach in improvin…
Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）
In this paper we demonstrate that $\textit{context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies}$. This contrasts to the most popular current methods for grammar induction, which focus on discovering $\textit{either}$ constituents $\textit{or}$ dependencies. Previous approaches to marry these two disparate syntactic formalisms (e.g. lexicalized PCFGs) have been plagued by sparsity, making them unsuitable for unsupervised grammar induction. However, in this work, we present novel neural models of lexicalized PCFGs which allow us to overcome s…
This paper presents an experiment in learning valences (subcategorization frames) from a 50 million word text corpus, based on a lexicalized probabilistic context free grammar. Distributions are estimated using a modified EM algorithm. We evaluate the acquired lexicon both by comparison with a dictionary and by entropy measures. Results show that our model produces highly accurate frame distributions.
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems in stochastic natural-language processing. Comparing the performance of PLTIGs with non-hierarchical N-gram models and PCFGs, we show that PLTIG combines the best aspects of both, with language modeling capability comparable to N-grams, and improved parsing performance over its non-lexicalized counterpart. Furthermore, training of PLTIGs displays faster convergence than PCFGs.
The Ohio State University（俄亥俄州立大学）；Harvard University（哈佛大学）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
There have been several recent attempts to improve the accuracy of grammar induction systems by bounding the recursive complexity of the induction model (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016; Jin et al., 2018). Modern depth-bounded grammar inducers have been shown to be more accurate than early unbounded PCFG inducers, but this technique has never been compared against unbounded induction within the same system, in part because most previous depth-bounding models are built around sequence models, the complexity of which grows exponentially with the maximum allowed d…
The paper describes an extensive experiment in inside-outside estimation of a lexicalized probabilistic context free grammar for German verb-final clauses. Grammar and formalism features which make the experiment feasible are described. Successive models are evaluated on precision and recall of phrase markup.
University of Rochester（罗切斯特大学）；Tencent AI Lab（腾讯AI实验室）
We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video. Existing methods of multi-modal grammar induction focus on learning syntactic grammars from text-image pairs, with promising results showing that the information from static images is useful in induction. However, videos provide even richer information, including not only static objects but also actions and state changes useful for inducing verb phrases. In this paper, we explore rich features (e.g. action, object, scene, audio, face, OCR and speech) from video…
Universidad del Cauca（考卡大学）；PRHLT Research Center（PRHLT研究中心）；Universitat Politécnica de Valéncia（瓦伦西亚理工大学）
We present a formal framework for the development of a family of discriminative learning algorithms for Probabilistic Context-Free Grammars (PCFGs) based on a generalization of criterion-H. First of all, we propose the H-criterion as the objective function and the Growth Transformations as the optimization method, which allows us to develop the final expressions for the estimation of the parameters of the PCFGs. And second, we generalize the H-criterion to take into account the set of reference interpretations and the set of competing interpretations, and we propose a new family of objective f…
Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs. We generalize chart constraints to more expressive grammar formalisms and describe a neural tagger which predicts chart constraints at very high precision. Our constraints accelerate both PCFG and TAG parsing, and combine effectively with other pruning techniques (coarse-to-fine and supertagging) for an overall speedup of two orders of magnitude, while improving accuracy.
ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）
Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are widely used structured models, both of which can be represented as factor graph grammars (FGGs), a powerful formalism capable of describing a wide range of models. Recent research found it beneficial to use large state spaces for HMMs and PCFGs. However, inference with large state spaces is computationally demanding, especially for PCFGs. To tackle this challenge, we leverage tensor rank decomposition (aka.\ CPD) to decrease inference computational complexities for a subset of FGGs subsuming HMMs and PCFGs. We appl…
The performance of PCFGs estimated from tree banks is sensitive to the particular way in which linguistic constructions are represented as trees in the tree bank. This paper presents a theoretical analysis of the effect of different tree representations for PP attachment on PCFG models, and introduces a new methodology for empirically examining such effects using tree transformations. It shows that one transformation, which copies the label of a parent node onto the labels of its children, can improve the performance of a PCFG model in terms of labelled precision and recall on held out data fr…
Robustness in a parser refers to an ability to deal with exceptional phenomena. A parser is robust if it deals with phenomena outside its normal range of inputs. This paper reports on a series of robustness evaluations of state-of-the-art parsers in which we concentrated on one aspect of robustness: its ability to parse sentences containing misspelled words. We propose two measures for robustness evaluation based on a comparison of a parser's output for grammatical input sentences and their noisy counterparts. In this paper, we use these measures to compare the overall robustness of the four e…
Natural language generation provides designers with methods for automatically generating text, e.g. for creating summaries, chatbots and game content. In practise, text generators are often either learned and hard to interpret, or created by hand using techniques such as grammars and templates. In this paper, we introduce a novel grammar induction algorithm for learning interpretable grammars for generative purposes, called Gitta. We also introduce the novel notion of template trees to discover latent templates in corpora to derive these generative grammars. By using existing human-created gra…
SingularityNET Foundation（奇点网基金会）；The Hong Kong Polytechnic University（香港理工大学）
A novel approach to automated learning of syntactic rules governing natural languages is proposed, based on using probabilities assigned to sentences (and potentially longer word sequences) by transformer neural network language models to guide symbolic learning processes like clustering and rule induction. This method exploits the learned linguistic knowledge in transformers, without any reference to their inner representations; hence, the technique is readily adaptable to the continuous appearance of more powerful language models. We show a proof-of-concept example of our proposed technique,…
Robots are widely collaborating with human users in diferent tasks that require high-level cognitive functions to make them able to discover the surrounding environment. A difcult challenge that we briefy highlight in this short paper is inferring the latent grammatical structure of language, which includes grounding parts of speech (e.g., verbs, nouns, adjectives, and prepositions) through visual perception, and induction of Combinatory Categorial Grammar (CCG) for phrases. This paves the way towards grounding phrases so as to make a robot able to understand human instructions appropriately d…
The inside-outside probabilities are typically used for reestimating Probabilistic Context Free Grammars (PCFGs), just as the forward-backward probabilities are typically used for reestimating HMMs. I show several novel uses, including improving parser accuracy by matching parsing algorithms to evaluation criteria; speeding up DOP parsing by 500 times; and 30 times faster PCFG thresholding at a given accuracy level. I also give an elegant, state-of-the-art grammar formalism, which can be used to compute inside-outside probabilities; and a parser description formalism, which makes it easy to de…
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）
Exploiting visual groundings for language understanding has recently been drawing much attention. In this work, we study visually grounded grammar induction and learn a constituency parser from both unlabeled text and its visual groundings. Existing work on this task (Shi et al., 2019) optimizes a parser via Reinforce and derives the learning signal only from the alignment of images and sentences. While their model is relatively accurate overall, its error distribution is very uneven, with low performance on certain constituents types (e.g., 26.2% recall on verb phrases, VPs) and high on other…
Recent progress in grammar induction has shown that grammar induction is possible without explicit assumptions of language-specific knowledge. However, evaluation of induced grammars usually has ignored phrasal labels, an essential part of a grammar. Experiments in this work using a labeled evaluation metric, RH, show that linguistically motivated predictions about grammar sparsity and use of categories can only be revealed through labeled evaluation. Furthermore, depth-bounding as an implementation of human memory constraints in grammar inducers is still effective with labeled evaluation on m…
Stanford University（斯坦福大学）；McGill University（麦吉尔大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）
The following technical report presents a formal approach to probabilistic minimalist grammar parameter estimation. We describe a formalization of a minimalist grammar. We then present an algorithm for the application of variational Bayesian inference to this formalization.
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical part-whole structure. In this work, we study grounded grammar induction of vision and language in a joint learning framework. Specifically, we present VLGrammar, a method that uses compound probabilistic context-free grammars (compound PCFGs) to induce the language grammar and the image grammar simultaneously. We propose a novel contrastive learning framewor…
Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is prohibitively expensive. This work aims to improve the induction strategy when there are few labels in the training data. We show that the most informative linguistic constituents are the higher nodes in the parse trees, typically denoting complex noun phrases and sentential clauses. They account for only 20% of all constituents. For inducing grammars from sparsely labeled training data (e.g., only higher-level const…
We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our grammar's rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this grammar is performed by collapsed variational inference, in which an amortized variational posterior is placed on the continuous variable, and the latent trees are marginaliz…
Most categorical models of meaning use a functor from the syntactic category to the semantic category. When semantic information is available, the problem of grammar induction can therefore be defined as finding preimages of the semantic types under this forgetful functor, lifting the information flow from the semantic level to a valid reduction at the syntactic level. We study the complexity of grammar induction, and show that for a variety of type systems, including pivotal and compact closed categories, the grammar induction problem is NP-complete. Our approach could be extended to linguist…
University of Canterbury（坎特伯雷大学）；University of Manchester（曼彻斯特大学）
This paper asks whether a distinction between production-based and perception-based grammar induction influences either (i) the growth curve of grammars and lexicons or (ii) the similarity between representations learned from independent sub-sets of a corpus. A production-based model is trained on the usage of a single individual, thus simulating the grammatical knowledge of a single speaker. A perception-based model is trained on an aggregation of many individuals, thus simulating grammatical generalizations learned from exposure to many different speakers. To ensure robustness, the experimen…
This paper describes continuing work on semantic frame slot filling for a command and control task using a weakly-supervised approach. We investigate the advantages of using retraining techniques that take the output of a hierarchical hidden markov model as input to two inductive approaches: (1) discriminative sequence labelers based on conditional random fields and memory-based learning and (2) probabilistic context-free grammar induction. Experimental results show that this setup can significantly improve F-scores without the need for additional information sources. Furthermore, qualitative …
Electrical and Computer Engineering, Carnegie Mellon University（卡内基梅隆大学电气与计算机工程系）；Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）
Most previous work on grammar induction focuses on learning phrasal or dependency structure purely from text. However, because the signal provided by text alone is limited, recently introduced visually grounded syntax models make use of multimodal information leading to improved performance in constituency grammar induction. However, as compared to dependency grammars, constituency grammars do not provide a straightforward way to incorporate visual information without enforcing language-specific heuristics. In this paper, we propose an unsupervised grammar induction model that leverages word c…
School of Information Science and Technology（信息科学与技术学院）；ShanghaiTech University（上海科技大学）
We study the impact of big models (in terms of the degree of lexicalization) and big data (in terms of the training corpus size) on dependency grammar induction. We experimented with L-DMV, a lexicalized version of Dependency Model with Valence and L-NDMV, our lexicalized extension of the Neural Dependency Model with Valence. We find that L-DMV only benefits from very small degrees of lexicalization and moderate sizes of training corpora. L-NDMV can benefit from big training data and lexicalization of greater degrees, especially when enhanced with good model initialization, and it achieves a r…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
Dependency grammar induction is the task of learning dependency syntax without annotated training data. Traditional graph-based models with global inference achieve state-of-the-art results on this task but they require $O(n^3)$ run time. Transition-based models enable faster inference with $O(n)$ time complexity, but their performance still lags behind. In this work, we propose a neural transition-based parser for dependency grammar induction, whose inference procedure utilizes rich neural features with $O(n)$ time complexity. We train the parser with an integration of variational inference, …
Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of regular grammars from positive and negative examples. Our model is fully explainable, its intermediate results are directly interpretable as partial parses, and it can be used to learn arbitrary regular grammars when provided with sufficient data. We find that our method consistently attains high recall and precision scores across a range of tests of varying co…
Seoul National University（首尔国立大学）；University of Chicago（芝加哥大学）
With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings. In line with such interest, we propose a novel method that assists us in investigating the extent to which pre-trained LMs capture the syntactic notion of constituency. Our method provides an effective way of extracting constituency trees from the pre-trained LMs without training. In addition, we report intriguing findings in the induced trees, including the fact that pre-trained LMs outperform other approaches in corre…
We propose a computational modeling framework for inducing combinatory categorial grammars from arbitrary behavioral data. This framework provides the analyst fine-grained control over the assumptions that the induced grammar should conform to: (i) what the primitive types are; (ii) how complex types are constructed; (iii) what set of combinators can be used to combine types; and (iv) whether (and to what) the types of some lexical items should be fixed. In a proof-of-concept experiment, we deploy our framework for use in distributional analysis. We focus on the relationship between s(emantic)…
We describe a corpus-based induction algorithm for probabilistic context-free grammars. The algorithm employs a greedy heuristic search within a Bayesian framework, and a post-pass using the Inside-Outside algorithm. We compare the performance of our algorithm to n-gram models and the Inside-Outside algorithm in three language modeling tasks. In two of the tasks, the training data is generated by a probabilistic context-free grammar and in both tasks our algorithm outperforms the other techniques. The third task involves naturally-occurring data, and in this task our algorithm does not perform…
A substantial thread of recent work on latent tree learning has attempted to develop neural network models with parse-valued latent variables and train them on non-parsing tasks, in the hope of having them discover interpretable tree structure. In a recent paper, Shen et al. (2018) introduce such a model and report near-state-of-the-art results on the target task of language modeling, and the first strong latent tree learning result on constituency parsing. In an attempt to reproduce these results, we discover issues that make the original results hard to trust, including tuning and even train…
Many NLP datasets have been found to contain shortcuts: simple decision rules that achieve surprisingly high accuracy. However, it is difficult to discover shortcuts automatically. Prior work on automatic shortcut detection has focused on enumerating features like unigrams or bigrams, which can find only low-level shortcuts, or relied on post-hoc model interpretability methods like saliency maps, which reveal qualitative patterns without a clear statistical interpretation. In this work, we propose to use probabilistic grammars to characterize and discover shortcuts in NLP datasets. Specificall…
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；Google Research（谷歌研究院）
There are two major classes of natural language grammar -- the dependency grammar that models one-to-one correspondences between words and the constituency grammar that models the assembly of one or several corresponded words. While previous unsupervised parsing methods mostly focus on only inducing one class of grammars, we introduce a novel model, StructFormer, that can simultaneously induce dependency and constituency structure. To achieve this, we propose a new parsing framework that can jointly generate a constituency tree and dependency graph. Then we integrate the induced dependency rel…
Dept of Computer Science, Univ of British Columbia（不列颠哥伦比亚大学计算机科学系）；Systems Biology Dept, Harvard Medical School（哈佛医学院系统生物学系）；Dept of Computer Science, MIT（麻省理工学院计算机科学系）；Google（谷歌）
This paper formulates a novel problem on graphs: find the minimal subset of edges in a fully connected graph, such that the resulting graph contains all spanning trees for a set of specifed sub-graphs. This formulation is motivated by an un-supervised grammar induction problem from computational linguistics. We present a reduction to some known problems and algorithms from graph theory, provide computational complexity results, and describe an approximation algorithm.
Ant Group（蚂蚁集团）；Shandong University（山东大学）；Hasso Plattner Institute（哈索·普拉特纳研究所）；University of Potsdam（波茨坦大学）
Recently CKY-based models show great potential in unsupervised grammar induction thanks to their human-like encoding paradigm, which runs recursively and hierarchically, but requires $O(n^3)$ time-complexity. Recursive Transformer based on Differentiable Trees (R2D2) makes it possible to scale to large language model pre-training even with complex tree encoder by introducing a heuristic pruning method. However, the rule-based pruning approach suffers from local optimum and slow inference issues. In this paper, we fix those issues in a unified method. We propose to use a top-down parser as a mo…
Grammar induction is the task of learning a grammar from a set of examples. Recently, neural networks have been shown to be powerful learning machines that can identify patterns in streams of data. In this work we investigate their effectiveness in inducing a regular grammar from data, without any assumptions about the grammar. We train a recurrent neural network to distinguish between strings that are in or outside a regular language, and utilize an algorithm for extracting the learned finite-state automaton. We apply this method to several regular languages and find unexpected results regard…
Path-dependent program induction under resource constraints explains human sequence learning
University of Tübingen（蒂宾根大学）；Center for Cognitive Science, Technical University Darmstadt（达姆施塔特工业大学认知科学中心）；Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所计算神经科学系）
Harvard University（哈佛大学）；University of Oxford（牛津大学）；DeepMind（深度思维）
Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order. Supervised RNNGs achieve strong language modeling and parsing performance, but require an annotated corpus of parse trees. In this work, we experiment with unsupervised learning of RNNGs. Since directly marginalizing over the space of latent trees is intractable, we instead apply amortized variational inference. To maximize the evidence lower bound, we develop an inference network p…
We propose a novel application of self-attention networks towards grammar induction. We present an attention-based supertagger for a refined type-logical grammar, trained on constructing types inductively. In addition to achieving a high overall type accuracy, our model is able to learn the syntax of the grammar's type system along with its denotational semantics. This lifts the closed world assumption commonly made by lexicalized grammar supertaggers, greatly enhancing its generalization potential. This is evidenced both by its adequate accuracy over sparse word types and its ability to corre…
Model-based language specification has applications in the implementation of language processors, the design of domain-specific languages, model-driven software development, data integration, text mining, natural language processing, and corpus-based induction of models. Model-based language specification decouples language design from language processing and, unlike traditional grammar-driven approaches, which constrain language designers to specific kinds of grammars, it needs general parser generators able to deal with ambiguities. In this paper, we propose Fence, an efficient bottom-up par…
Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories. In addition to the tagset, we develop a mapping from 25 different treebank tagsets to this universal set. As a result, when combined with the original treebank data, this universal tagset and mapping produce a dataset consisting of common parts-of-speech for 22 different languages. We highlight the use of this resource via two experiments, including one that reports competitive accuracies for unsupervi…
New Zealand Institute for Language, Brain and Behaviour（新西兰语言、大脑与行为研究所）；University of Canterbury（坎特伯雷大学）；Geospatial Research Institute Toi Hangarau（Toi Hangarau地理空间研究所）
This paper analyses the degree to which dialect classifiers based on syntactic representations remain stable over space and time. While previous work has shown that the combination of grammar induction and geospatial text classification produces robust dialect models, we do not know what influence both changing grammars and changing populations have on dialect models. This paper constructs a test set for 12 dialects of English that spans three years at monthly intervals with a fixed spatial distribution across 1,120 cities. Syntactic representations are formulated within the usage-based Constr…
In this thesis I present various algorithms for the unsupervised machine learning of aspects of natural languages using a variety of statistical models. The scientific object of the work is to examine the validity of the so-called Argument from the Poverty of the Stimulus advanced in favour of the proposition that humans have language-specific innate knowledge. I start by examining an a priori argument based on Gold's theorem, that purports to prove that natural languages cannot be learned, and some formal issues related to the choice of statistical grammars rather than symbolic grammars. I pr…
