scholarly journals Combined Distributional and Logical Semantics

2013 ◽  
Vol 1 ◽  
pp. 179-192 ◽  
Author(s):  
Mike Lewis ◽  
Mark Steedman
Keyword(s):  
Argument Structure ◽  
Clustering Algorithm ◽  
Question Answering ◽  
Formal Semantics ◽  
Function Words ◽  
New Approach ◽  
Predicate Argument Structure ◽  
Logical Semantics ◽  
Mapping Language

We introduce a new approach to semantics which combines the benefits of distributional and formal logical semantics. Distributional models have been successful in modelling the meanings of content words, but logical semantics is necessary to adequately represent many function words. We follow formal semantics in mapping language to logical representations, but differ in that the relational constants used are induced by offline distributional clustering at the level of predicate-argument structure. Our clustering algorithm is highly scalable, allowing us to run on corpora the size of Gigaword. Different senses of a word are disambiguated based on their induced types. We outperform a variety of existing approaches on a wide-coverage question answering task, and demonstrate the ability to make complex multi-sentence inferences involving quantifiers on the FraCaS suite.

Dependency parsing of Polish

2019 ◽  
Vol 55 (2) ◽  
pp. 305-337 ◽  
Author(s):  
Alina Wróblewska ◽  
Piotr Rybak
Keyword(s):  
Language Processing ◽  
Argument Structure ◽  
Question Answering ◽  
State Of The Art ◽  
Dependency Parsing ◽  
Dependency Theory ◽  
Crucial Issue ◽  
Experimental Part ◽  
Predicate Argument Structure

Abstract The predicate-argument structure transparently encoded in dependency-based syntactic representations supports machine translation, question answering, information extraction, etc. The quality of dependency parsing is therefore a crucial issue in natural language processing. In the current paper we discuss the fundamental ideas of the dependency theory and provide an overview of selected dependency-based resources for Polish. Furthermore, we present some state-of-the-art dependency parsing systems whose models can be estimated on correctly annotated data. In the experimental part, we provide an in-depth evaluation of these systems on Polish data. Our results show that graph-based parsers, even those without any neural component, are better suited for Polish than transition-based parsing systems.

Niuean

2020 ◽  
Author(s):  
Diane Massam
Keyword(s):  
Word Order ◽  
Argument Structure ◽  
Word Formation ◽  
Left Periphery ◽  
Sentence Structure ◽  
Noun Incorporation ◽  
The Pacific ◽  
Theta Role ◽  
Predicate Argument Structure

This book presents a detailed descriptive and theoretical examination of predicate-argument structure in Niuean, a Polynesian language within the Oceanic branch of the Austronesian family, spoken mainly on the Pacific island of Niue and in New Zealand. Niuean has VSO word order and an ergative case-marking system, both of which raise questions for a subject-predicate view of sentence structure. Working within a broadly Minimalist framework, this volume develops an analysis in which syntactic arguments are not merged locally to their thematic sources, but instead are merged high, above an inverted extended predicate which serves syntactically as the Niuean verb, later undergoing movement into the left periphery of the clause. The thematically lowest argument merges as an absolutive inner subject, with higher arguments merging as applicatives. The proposal relates Niuean word order and ergativity to its isolating morphology, by equating the absence of inflection with the absence of IP in Niuean, which impacts many aspects of its grammar. As well as developing a novel analysis of clause and argument structure, word order, ergative case, and theta role assignment, the volume argues for an expanded understanding of subjecthood. Throughout the volume, many other topics are also treated, such as noun incorporation, word formation, the parallel internal structure of predicates and arguments, null arguments, displacement typology, the role of determiners, and the structure of the left periphery.

A Typed Feature-based Grammar of Danish

1997 ◽  
Vol 20 (1) ◽  
pp. 31-62
Author(s):  
Nancy L. Underwood
Keyword(s):  
Argument Structure ◽  
Phrase Structure ◽  
Inflectional Morphology ◽  
Feature Structure ◽  
Formal Framework ◽  
Feature Based ◽  
Predicate Argument Structure

This paper presents an overview of the first broad coverage grammatical description of Danish in a Typed Feature Structure (TFS) based unification formalism inspired by HPSG. These linguistic specifications encompass phenomena within inflectional morphology, phrase structure and predicate argument structure, and have been developed with a view to implementation. The emphasis on implementability and re-usability of the specifications has led to the adoption of a rather leaner formal framework than that underlying HPSG. However, the paper shows that the adoption of such a framework does not lead to a loss of expressibility, but in fact enables certain phenomena, such as the interface between morphology and syntax and local discontinuities, to be treated in a simple and elegant fashion.

scholarly journals Syntax Role for Neural Semantic Role Labeling

2021 ◽  
pp. 1-48
Author(s):  
Zuchao Li ◽  
Hai Zhao ◽  
Shexia He ◽  
Jiaxun Cai
Keyword(s):  
Argument Structure ◽  
Large Scale ◽  
Language Models ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Empirical Survey ◽  
Learning Framework ◽  
Syntactic Information ◽  
Feature Based ◽  
Predicate Argument Structure

Abstract 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 language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruningbased and syntax feature-based. Experiments are conducted on the CoNLL-2005, 2009, and 2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.

scholarly journals The Bilingual Mental Lexicon and Lemmatic Transfer in Second Language Learning

2020 ◽  
Vol 2 (3) ◽  
pp. p43
Author(s):  
Longxing Wei
Keyword(s):  
Second Language ◽  
Language Learning ◽  
Argument Structure ◽  
Mental Lexicon ◽  
Language Transfer ◽  
L1 Transfer ◽  
Abstract Approach ◽  
Lexical Structure ◽  
L2 Learning ◽  
Predicate Argument Structure

There have been numerous studies of first Language (L1) transfer in second Language (L2) learning. Various models have been proposed to explore the sources of language transfer and have also caused many controversies over the nature of language transfer and its effects on interlanguage. Different from most previous studies remaining at a surface level of observation, this study proposes an abstract approach, which is abstract because it goes beyond any superficial observation and description by exploring the nature and activity of the bilingual mental lexicon in L2 learning. This approach adopts the Bilingual Lemma Activation Model (BLAM) (Wei, 2006a, 2006b) and tests its crucial assumptions and claims: The bilingual mental lexicon does not simply contain lexemes but abstract entries, called “lemmas”, about them; lemmas in the bilingual mental lexicon are language-specific; language-specific lemmas in the bilingual mental lexicon are in contact in L2 learning, lemmas underlying L1 abstract lexical structure may replace those underlying L2 abstract lexical structure. Lemmas in the bilingual mental lexicon are about three levels of abstract lexical structure: lexical-conceptual structure, predicate-argument structure, and morphological realization patterns. The typical instances of L1 lemma transfer in L2 learning are discussed and explained in support of the BLAM.

scholarly journals Czasowniki mentalne i czasowniki emocji w opisie semantyczno-syntaktycznym

2017 ◽  
Vol 52 ◽  
pp. 139-163
Author(s):  
Małgorzata Korytkowska
Keyword(s):  
Argument Structure ◽  
Main Issue ◽  
Semantic Features ◽  
Verb Classes ◽  
Predicate Argument Structure ◽  
Basic Semantic

Mental and emotional verbs in semantic and syntactic descriptionThe main issue of this article concerns relations between the semantic plane of the sentence, which is presented by means of notions of predicate argument structure, and the plane of formal realisation of this structure. The existing attitudes to the studied verb classes are presented. Then rules governing the model of description used are specified (the article has been written within an elaborate scientific grant concerning Bulgarian, Polish and Russian). Obligatory semantic features of both classes are pointed out, followed by an elaboration on the scope of analysis of semantic and syntactic phenomena. This scope is determined by basic semantic sentence categories on which comparative, including contrastive, research is based. Drawing on examples of particular units studied, I then discuss the effectiveness of the analysis which enables comparing differences between sets of sentence structures allowable for each class studied. Those differences stem from semantic differences typical of those classes. Czasowniki mentalne i czasowniki emocji w opisie semantyczno-syntaktycznymTematyka artykułu dotyczy relacji między płaszczyzną semantyczną zdania, ujętą w terminach struktury predykatowo-argumentowej, a płaszczyzną realizacji formalnej tej struktury. Zarysowane zostały dotychczasowe podejścia do opisu badanych klas czasowników oraz sprecyzowano ustalenia dotyczące zastosowanego w artykule modelu opisu (artykuł powstał w związku z realizacją obszernego grantu dotyczącego języka bułgarskiego, polskiego i rosyjskiego). Wskazano obligatoryjne dla obu klas cechy semantyczne oraz scharakteryzowano zakres analizy zjawisk semantyczno-składniowych. Zakres ten wyznaczają podstawowe semantyczne kategorie zdaniowe, których badanie stanowi podstawę dla porównań, także porównań konfrontatywnych. Zaprezentowane zostały przykłady opracowania wybranych jednostek oraz wskazana skuteczność analizy, która pozwala ukazać różnice między zbiorami dopuszczalnych dla każdej z badanych klas struktur zdaniowych. Różnice te wynikają z charakteryzujących te klasy różnic semantycznych.

Sign in / Sign up

Export Citation Format

Share Document