Building robust natural language understanding systems will require a clear characterization of whether and how various linguistic meaning representations complement each other. To perform a systematic comparative analysis, we evaluate the mapping between meaning representations from different frameworks using two complementary methods: (i) a rule-based converter, and (ii) a supervised delexicalized parser that parses to one framework using only information from the other as features. We apply these methods to convert the STREUSLE corpus (with syntactic and lexical semantic annotations) to UCCA (a graph-structured full-sentence meaning representation). Both methods yield surprisingly accurate target representations, close to fully supervised UCCA parser quality---indicating that UCCA annotations are partially redundant with STREUSLE annotations. Despite this substantial convergence between frameworks, we find several important areas of divergence.
Yuanpei College, Peking University（北京大学元培学院）；Key Laboratory of Computational Linguistics, School of EECS, Peking University（北京大学电子信息工程学院计算语言学重点实验室）
Copying mechanism has been commonly used in neural paraphrasing networks and other text generation tasks, in which some important words in the input sequence are preserved in the output sequence. Similarly, in machine translation, we notice that there are certain words or phrases appearing in all good translations of one source text, and these words tend to convey important semantic information. Therefore, in this work, we define words carrying important semantic meanings in sentences as semantic core words. Moreover, we propose an MT evaluation approach named Semantically Weighted Sentence Si…
This is a work-in-progress report, which aims to share preliminary results of a novel sequence-to-sequence schema for dependency parsing that relies on a combination of a BiLSTM and two Pointer Networks (Vinyals et al., 2015), in which the final softmax function has been replaced with the logistic regression. The two pointer networks co-operate to develop a latent syntactic knowledge, by learning the lexical properties of "selection" and the lexical properties of "selectability", respectively. At the moment and without fine-tuning, the parser implementation gets a UAS of 93.14% on the English …
A fundamental question in neurolinguistics concerns the brain regions involved in syntactic and semantic processing during speech comprehension, both at the lexical (word processing) and supra-lexical levels (sentence and discourse processing). To what extent are these regions separated or intertwined? To address this question, we trained a lexical language model, Glove, and a supra-lexical language model, GPT-2, on a text corpus from which we selectively removed either syntactic or semantic information. We then assessed to what extent these information-restricted models were able to predict t…
Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing parsers. We present a simple but highly effective approach for training neural LMs using both lexical and syntactic information, and a novel approach for applying such LMs to unparsed text using sequential Monte Carlo sampling. In experiments on a range of corpora and corpus sizes, we show our approach consistently outperforms standard lexical LMs in charac…
This paper discusses SYNTAGMA, a rule based NLP system addressing the tricky issues of syntactic ambiguity reduction and word sense disambiguation as well as providing innovative and original solutions for constituent generation and constraints management. To provide an insight into how it operates, the system's general architecture and components, as well as its lexical, syntactic and semantic resources are described. After that, the paper addresses the mechanism that performs selective parsing through an interaction between syntactic and semantic information, leading the parser to a coherent…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
As speakers turn their thoughts into sentences, they maintain a balance between the complexity of words and syntax. However, it is unclear whether this syntax-lexicon tradeoff is unique to the spoken language production that is under the pressure of rapid online processing. Alternatively, it is possible that the tradeoff is a basic property of language irrespective of the modality of production. This work evaluates the relationship between the complexity of words and syntactic rules in the written language of neurotypical individuals on three different topics. We found that similar to speaking…
Utrecht University（乌得勒支大学）；Queen Mary University of London（伦敦玛丽女王大学）
Sadrzadeh et al (2013) present a compositional distributional analysis of relative clauses in English in terms of the Frobenius algebraic structure of finite dimensional vector spaces. The analysis relies on distinct type assignments and lexical recipes for subject vs object relativisation. The situation for Dutch is different: because of the verb final nature of Dutch, relative clauses are ambiguous between a subject vs object relativisation reading. Using an extended version of Lambek calculus, we present a compositional distributional framework that accounts for this derivational ambiguity,…
Results from a recent neuroimaging study on spoken sentence comprehension have been interpreted as evidence for cortical entrainment to hierarchical syntactic structure. We present a simple computational model that predicts the power spectra from this study, even though the model's linguistic knowledge is restricted to the lexical level, and word-level representations are not combined into higher-level units (phrases or sentences). Hence, the cortical entrainment results can also be explained from the lexical properties of the stimuli, without recourse to hierarchical syntax.
Wuhan University（武汉大学）；Guangdong University of Foreign Studies（广东外语外贸大学）
Lexical chain consists of cohesion words in a document, which implies the underlying structure of a text, and thus facilitates downstream NLP tasks. Nevertheless, existing work focuses on detecting the simple surface lexicons with shallow syntax associations, ignoring the semantic-aware lexical compounds as well as the latent semantic frames, (e.g., topic), which can be much more crucial for real-world NLP applications. In this paper, we introduce a novel task, Nominal Compound Chain Extraction (NCCE), extracting and clustering all the nominal compounds that share identical semantic topics. In…
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…
We present a semantic role labeling resource for Hebrew built semi-automatically through annotation projection from English. This corpus is derived from the multilingual OpenSubtitles dataset and includes short informal sentences, for which reliable linguistic annotations have been computed. We provide a fully annotated version of the data including morphological analysis, dependency syntax and semantic role labeling in both FrameNet and PropBank styles. Sentences are aligned between English and Hebrew, both sides include full annotations and the explicit mapping from the English arguments to …
Inria（法国国家信息与自动化研究所）；Facebook AI Research（脸书人工智能研究院）；École normale supérieure（巴黎高等师范学院）；PSL University（巴黎文理研究大学）；CNRS（法国国家科学研究中心）
The activations of language transformers like GPT-2 have been shown to linearly map onto brain activity during speech comprehension. However, the nature of these activations remains largely unknown and presumably conflate distinct linguistic classes. Here, we propose a taxonomy to factorize the high-dimensional activations of language models into four combinatorial classes: lexical, compositional, syntactic, and semantic representations. We then introduce a statistical method to decompose, through the lens of GPT-2's activations, the brain activity of 345 subjects recorded with functional magn…
This paper proposes a way to compute the meanings associated with sentences with generic noun phrases corresponding to the generalized quantifier most. We call these generics specimens and they resemble stereotypes or prototypes in lexical semantics. The meanings are viewed as logical formulae that can thereafter be interpreted in your favourite models. To do so, we depart significantly from the dominant Fregean view with a single untyped universe. Indeed, our proposal adopts type theory with some hints from Hilbert ε-calculus (Hilbert, 1922; Avigad and Zach, 2008) and from medieval philosophy…
In this paper we study, analyse and comment rhetorical figures present in some of most interesting poetry of the first half of the twentieth century. These figures are at first traced back to some famous poet of the past and then compared to classical Latin prose. Linguistic theory is then called in to show how they can be represented in syntactic structures and classified as noncanonical structures, by positioning discontinuous or displaced linguistic elements in Spec XP projections at various levels of constituency. Then we introduce LFG (Lexical Functional Grammar) as the theory that allows…
Tree adjoining grammars (TAGs) provide an ample tool to capture syntax of many Indian languages. Tamil represents a special challenge to computational formalisms as it has extensive agglutinative morphology and a comparatively difficult argument structure. Modelling Tamil syntax and morphology using TAG is an interesting problem which has not been in focus even though TAGs are over 4 decades old, since its inception. Our research with Tamil TAGs have shown us that we can not only represent syntax of the language, but to an extent mine out semantics through dependency resolution of the sentence…
McGovern Medical School, UTHealth（UTHealth麦戈文医学院）；Texas Institute for Restorative Neurotechnologies, UTHealth（UTHealth德克萨斯修复神经技术研究所）
A comprehensive model of natural language processing in the brain must accommodate four components: representations, operations, structures and encoding. It further requires a principled account of how these components mechanistically, and causally, relate to each another. While previous models have isolated regions of interest for structure-building and lexical access, many gaps remain with respect to bridging distinct scales of neural complexity. By expanding existing accounts of how neural oscillations can index various linguistic processes, this article proposes a neurocomputational archit…
A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into unseen sequences. We present a systematic comparison of sequence-to-sequence models and models guided by compositional principles on the recent COGS corpus (Kim and Linzen, 2020). Though seq2seq models can perform well on lexical tasks, they perform with near-zero accuracy on structural generalization tasks that require novel syntactic structures; this holds true even when they are trained to predict syntax instead o…
Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures, the direct similarity comparison between them exhibits weak sensitivity to word order and structural differences in given sentences. A single similarity score further makes the comparison process hard to interpret. Therefore, we here propose to combine sentence encoders with an alignment component by representing each sentence as a list of predicate-argument …
Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks
Paris Brain Institute（巴黎脑研究所）；Laboratoire de Sciences Cognitives et Psycholinguistique (LSCP)（认知科学与心理语言学实验室）；Département d’Etudes Cognitives（认知研究部）；École Normale Supérieure PSL University（巴黎高等师范学院）；CNRS（国家科学研究中心）；Laboratoire des Systèmes Perceptifs（感知系统实验室）；Meta AI
Syntactic structure of sentences in a document substantially informs about its authorial writing style. Sentence representation learning has been widely explored in recent years and it has been shown that it improves the generalization of different downstream tasks across many domains. Even though utilizing probing methods in several studies suggests that these learned contextual representations implicitly encode some amount of syntax, explicit syntactic information further improves the performance of deep neural models in the domain of authorship attribution. These observations have motivated…
Higher Institute for Applied Sciences and Technology (HIAST)（高等应用科学与技术学院）；Arab International University (AIU)（阿拉伯国际大学）
Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-to-process representations, such as lists of features or embedding-based vector representations. These NLP-based representations are usually used at a later stage as inputs for machine learning techniques or rule-based methods. Thus, requirements representations play a major role in determining the accuracy of d…
