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 correctly demarcating adverb phrases in sentences.
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…
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…
Natural Language Processing (NLP) has become one of the leading application areas in the current Artificial Intelligence boom. Transfer learning has enabled large deep learning neural networks trained on the language modeling task to vastly improve performance in almost all downstream language tasks. Interestingly, when the language models are trained with data that includes software code, they demonstrate remarkable abilities in generating functioning computer code from natural language specifications. We argue that this creates a conundrum for the claim that eliminative neural models are a r…
In this paper we present NLML (Natural Language Markup Language), a markup language to describe the syntactic and semantic structure of any grammatically correct English expression. At first the related works are analyzed to demonstrate the necessity of the NLML: simple form, easy management and direct storage. Then the description of the English grammar with NLML is introduced in details in three levels: sentences (with different complexities, voices, moods, and tenses), clause (relative clause and noun clause) and phrase (noun phrase, verb phrase, prepositional phrase, adjective phrase, adve…
Translation models based on hierarchical phrase-based statistical machine translation (HSMT) have shown better performances than the non-hierarchical phrase-based counterparts for some language pairs. The standard approach to HSMT learns and apply a synchronous context-free grammar with a single non-terminal. The hypothesis behind the grammar refinement algorithm presented in this work is that this single non-terminal is overloaded, and insufficiently discriminative, and therefore, an adequate split of it into more specialised symbols could lead to improved models. This paper presents a method…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；University of Edinburgh（爱丁堡大学）
In this work, we study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of contextualized representations. Instead of seeking alignments to existing well-defined annotations, we infer this latent network in a fully unsupervised way using a structured variational autoencoder. The induced states not only serve as anchors that mark the topology (neighbors and connectivity) of the representation manifold but also reveal the internal mechanism…
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…
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…
In numerous domains in cognitive science it is often useful to have a source for randomly generated corpora. These corpora may serve as a foundation for artificial stimuli in a learning experiment (e.g., Ellefson & Christiansen, 2000), or as input into computational models (e.g., Christiansen & Dale, 2001). The following compact and general C program interprets a phrase-structure grammar specified in a text file. It follows parameters set at a Unix or Unix-based command-line and generates a corpus of random sentences from that grammar.
Phrase-structure grammars are effective models for important syntactic and semantic aspects of natural languages, but can be computationally too demanding for use as language models in real-time speech recognition. Therefore, finite-state models are used instead, even though they lack expressive power. To reconcile those two alternatives, we designed an algorithm to compute finite-state approximations of context-free grammars and context-free-equivalent augmented phrase-structure grammars. The approximation is exact for certain context-free grammars generating regular languages, including all …
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,…
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…
The central role of the lexicon in Meaning-Text Theory (MTT) and other dependency-based linguistic theories cannot be replicated in linguistic theories based on context-free grammars (CFGs). We describe Tree Adjoining Grammar (TAG) as a system that arises naturally in the process of lexicalizing CFGs. A TAG grammar can therefore be compared directly to an Meaning-Text Model (MTM). We illustrate this point by discussing the computational complexity of certain non-projective constructions, and suggest a way of incorporating locality of word-order definitions into the Surface-Syntactic Component …
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.
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 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 comp…
A Shake and Bake machine translation algorithm for Head-Driven Phrase Structure Grammar is introduced based on the algorithm proposed by Whitelock for unification categorial grammar. The translation process is then analysed to determine where the potential sources of inefficiency reside, and some proposals are introduced which greatly improve the efficiency of the generation algorithm. Preliminary empirical results from tests involving a small grammar are presented, and suggestions for greater improvement to the algorithm are provided.
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…
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…
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…
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…
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…
This study analyses Turkish syntax from an informational point of view. Sign based linguistic representation and principles of HPSG (Head-driven Phrase Structure Grammar) theory are adapted to Turkish. The basic informational elements are nested and inherently sorted feature structures called signs. In the implementation, logic programming tool ALE (Attribute Logic Engine) which is primarily designed for implementing HPSG grammars is used. A type and structure hierarchy of Turkish language is designed. Syntactic phenomena such a s subcategorization, relative clauses, constituent order variatio…
Head-driven phrase structure grammar (HPSG) enjoys a uniform formalism representing rich contextual syntactic and even semantic meanings. This paper makes the first attempt to formulate a simplified HPSG by integrating constituent and dependency formal representations into head-driven phrase structure. Then two parsing algorithms are respectively proposed for two converted tree representations, division span and joint span. As HPSG encodes both constituent and dependency structure information, the proposed HPSG parsers may be regarded as a sort of joint decoder for both types of structures and…
Finding simple, non-recursive, base noun phrases is an important subtask for many natural language processing applications. While previous empirical methods for base NP identification have been rather complex, this paper instead proposes a very simple algorithm that is tailored to the relative simplicity of the task. In particular, we present a corpus-based approach for finding base NPs by matching part-of-speech tag sequences. The training phase of the algorithm is based on two successful techniques: first the base NP grammar is read from a ``treebank'' corpus; then the grammar is improved by…
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…
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…
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…
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, …
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)…
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.
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…
The paper presents some aspects involved in the formalization and implementation of HPSG theories. As basis, the logical setups of Carpenter (1992) and King (1989, 1994) are briefly compared regarding their usefulness as basis for HPSGII (Pollard and Sag 1994). The possibilities for expressing HPSG theories in the HPSGII architecture and in various computational systems (ALE, Troll, CUF, and TFS) are discussed. Beside a formal characterization of the possibilities, the paper investigates the specific choices for constraints with certain linguistic motivations, i.e. the lexicon, structure licen…
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…
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…
University of Colorado, Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
Past approaches to translate a phrase in a language L1 to a language L2 using a dictionary-based approach require grammar rules to restructure initial translations. This paper introduces a novel method without using any grammar rules to translate a given phrase in L1, which does not exist in the dictionary, to L2. We require at least one L1-L2 bilingual dictionary and n-gram data in L2. The average manual evaluation score of our translations is 4.29/5.00, which implies very high quality.
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；University of Illinois at Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校）
Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any linguistic annotation of phrase segmentation. Instead, we define syntactic heights and phrase segmentation rules, enabling the model to automatically induce phrases, recognize their task-specific heads, and generate phrase embeddings in an unsupervised learning manner. Our method can easily be applied to language models with different network architectures since…
Sony Computer Science Laboratories Inc.（索尼计算机科学实验室公司）；University of Bremen（不来梅大学）
We present a system for generating and understanding of dynamic and static spatial relations in robotic interaction setups. Robots describe an environment of moving blocks using English phrases that include spatial relations such as "across" and "in front of". We evaluate the system in robot-robot interactions and show that the system can robustly deal with visual perception errors, language omissions and ungrammatical utterances.
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…
Information Sciences Institute（信息科学研究所）；University of Southern California（南加州大学）
Current research in automatic single document summarization is dominated by two effective, yet naive approaches: summarization by sentence extraction, and headline generation via bag-of-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techniques have been developed to extract appropriate training data for them from existing document/abstract and document/headline corpora. We believe th…
Einstein Center for Neurosciences Berlin（柏林爱因斯坦神经科学中心）；Technical University Berlin（柏林工业大学）；Imperial College London（帝国理工学院）
Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a sample inefficient exploration phase or lack semantic interpretability. Humans, on the other hand, efficiently detect hierarchical sub-structures induced by their surroundings. It has been argued that this inference process universally applies to language, logical reasoning as well as motor control. Therefore, we propose a cognitive-inspired Reinforcement Learn…
Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；Pompeu Fabra University（庞培法布拉大学）
We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Experiments show that they provide better parsing in English than any single previously published supervised generative model and better language modeling than state-of-the-art sequential RNNs in English and Chinese.
