Choosing the Word Most Typical in Context Using a Lexical Co-occurrence Network

This paper presents a partial solution to a component of the problem of lexical choice: choosing the synonym most typical, or expected, in context. We apply a new statistical approach to representing the context of a word through lexical co-occurrence networks. The implementation was trained and evaluated on a large corpus, and results show that the inclusion of second-order co-occurrence relations improves the performance of our implemented lexical choice program.

• Publication year

  1997

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  1997-07-07

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/976909.979684arXiv cs/9811009
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Lexical semantics and knowledge representation in multilingual sentence generation

  1996cited by this paper
• Combining Trigram-Based and Feature-Based Methods for Context-Sensitive Spelling Correction

  1996cited by this paper
• Learning Similarity-based Word Sense Disambiguation from Sparse Data

  1996cited by this paper
• Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach

  1996cited by this paper
• Near-synonymy and the structure of lexical knowledge

  1995cited by this paper
• Computational approaches to the lexicon

  1994cited by this paper
• The semantic and stylistic differentiation of synonyms and near-synonyms

  1993cited by this paper
• Using argumentation to control lexical choice: a functional unification implementation

  1993cited by this paper
• Word-Sense Disambiguation Using Statistical Models of Roget's Categories Trained on Large Corpora

  1992cited by this paper

• Monitoring the Semantic Change of COVID-19-related Expressions Using Dynamic Word Embeddings

  2025cites this paper
• Personalized AR Content and POI Recommendation in Mobile Cultural Heritage Systems Using Semantic Relatedness

  2025cites this paper
• The Impact of Topological Structure, Product Category, and Online Reviews on Co-Purchase: A Network Perspective

  2023cites this paper
• Network Analysis on Emotional Responses in International Disputes

  2020cites this paper
• A History and Theory of Textual Event Detection and Recognition

  2020cites this paper
• Chinese Long and Short Form Choice Exploiting Neural Network Language Modeling Approaches

  2020cites this paper
• Assessing the Helpfulness of Learning Materials with Inference-Based Learner-Like Agent

  2020cites this paper
• Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet

  2020cites this paper
• Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity

  2020cites this paper
• Mandarin Speakers’ Conceptualization of Force and Motion in the Semantics of Pull Verbs of Hand Action in Mandarin Chinese

  2019cites this paper
• Current psychology letters, 18, Vol. 1, 2006 | 2006

  2019cites this paper
• Context Analysis for Computer-Assisted Near-Synonym Learning

  2019cites this paper
• Single document keyword extraction via quantifying higher-order structural features of word co-occurrence graph

  2019cites this paper
• Second-order Co-occurrence Sensitivity of Skip-Gram with Negative Sampling

  2019cites this paper
• Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support Systems

  2019cites this paper
• Comparison of Measurements by the Betweenness Centrality and Subjective Experiment on the Word Priority of Tweets

  2018cites this paper
• MeetupNet Dublin: Discovering Communities in Dublin's Meetup Network

  2018cites this paper
• Multilevel News Networks

  2018cites this paper
• Towards a Better Learning of Near-Synonyms: Automatically Suggesting Example Sentences via Fill in the Blank

  2017cites this paper
• Temporal Multi-layer Network Construction from Major News Events

  2016cites this paper
• Varia Effects of High-Order Co-occurrences on Word Semantic Similarity

  2016cites this paper
• Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models

  2016influential citation
• Near-synonym substitution using a discriminative vector space model

  2016cites this paper
• Automatically Suggesting Example Sentences of Near-Synonyms for Language Learners

  2016cites this paper
• A Real-Time N-Gram Approach to Choosing Synonyms Based on Context

  2015cites this paper
• Predicting word choice in affective text†

  2015influential citation
• Extraction of Temporal Networks from Term Co-Occurrences in Online Textual Sources

  2014cites this paper
• Analysis of Problem Awareness in Hygiene Mask Wearers: A Cross-Sectional Survey

  2014cites this paper
• Understanding Financial News with Multi-layer Network Analysis

  2014cites this paper
• Independent component analysis for near-synonym choice

  2013cites this paper
• Uncovering Distributional Differences between Synonyms and Antonyms in a Word Space Model

  2013cites this paper
• Pattern-Based Distinction of Paradigmatic Relations for German Nouns, Verbs, Adjectives

  2013cites this paper
• Natural Language Processing Methods for Attitudinal Near-Synonymy

  2013cites this paper
• Selectional Preferences for Semantic Role Classification

  2013cites this paper
• The Hermeneutics Of The Hard Drive: Using Narratology, Natural Language Processing, And Knowledge Management To Improve The Effectiveness Of The Digital Forensic Process

  2013cites this paper
• Finding Meaning in Context Using Graph Algorithms in Mono- and Cross-lingual Settings

  2013cites this paper
• Multi-word tokenization for natural language processing

  2013cites this paper
• Synonymy Extraction From Semantic Networks Using String and Graph Kernel Methods

  2012cites this paper
• 應用跳脫語言模型於同義詞取代之研究 (Skip N-gram Modeling for Near-Synonym Choice) [In Chinese]

  2012cites this paper
• Exploring Extensive Linguistic Feature Sets in Near-Synonym Lexical Choice

  2012cites this paper
• Explorations in lexical sample and all-words lexical substitution

  2012cites this paper
• Creating a system for lexical substitutions from scratch using crowdsourcing

  2012influential citation
• Spell Checking in Spanish: The Case of Diacritic Accents

  2012cites this paper
• 應用跳脫語言模型於同義詞取代之研究 (Skip N-gram Modeling for Near-Synonym Choice) [In Chinese].

  2012cites this paper
• Developing and Evaluating a Computer-Assisted Near-Synonym Learning System

  2012cites this paper
• Exploratory analysis of the interrelations between co-located boolean spatial features using network graphs

  2012cites this paper
• A Baseline System for Chinese Near-Synonym Choice

  2011cites this paper
• An unsupervised approach to detecting and correcting errors in text

  2011influential citation
• Large-vocabulary Lexical Choice with Rich Context Features

  2011influential citation
• Exploiting Syntactic and Distributional Information for Spelling Correction with Web-Scale N-gram Models

  2011cites this paper
• Application of Machine Learning Algorithms for Automatic Knowledge Acquisition and Readability Analysis Technical Report

  2011cites this paper
• Near-synonym Lexical Choice in Latent Semantic Space

  2010cites this paper
• A Comparative analysis: QA evaluation questions versus real-world queries

  2010cites this paper
• Aspect presence verification conditional on other aspects

  2010cites this paper
• Corpus-based Semantic Class Mining: Distributional vs. Pattern-Based Approaches

  2010cites this paper
• Unified linear subspace approach to semantic analysis

  2010cites this paper
• Requirements for the design of a personal document-management system

  2010cites this paper
• Near-Synonym Choice using a 5-gram Language Model

  2010influential citation
• Discriminative Training for Near-Synonym Substitution

  2010cites this paper
• A higher order collective classifier

  2009cites this paper
• A Higher Order Collective Classifier for detecting and classifying network events

  2009cites this paper
• Co-Dispersion: A Windowless Approach to Lexical Association

  2009cites this paper
• Combining Syntactic Co-occurrences and Nearest Neighbours in Distributional Methods to Remedy Data Sparseness.

  2009cites this paper
• Leveraging Higher Order Dependencies between Features for Text Classification

  2009cites this paper
• A Sensemaking-based Information Foraging and Summarization System in Business Environments

  2009cites this paper
• NAACL HLT 2009 Unsupervised and Minimally Supervised Learning of Lexical Semantics

  2009cites this paper
• Variance-based clustering methods and higher order data transformations and their applications

  2009cites this paper
• A Higher Order Collective Classifier By Vikas Menon

  2009cites this paper
• Impacts of Visualisation, Interaction and Immersion on Learning Using an Agent-Based Training Simulation

  2008cites this paper
• A Graph-theoretic Model of Lexical Syntactic Acquisition

  2008cites this paper
• Acquisition automatique de sens pour la désambiguïsation et la sélection lexicale en traduction

  2008cites this paper
• Acquiring Word Similarities with Higher Order Association Mining

  2007cites this paper
• SEMANTIC SIMILARITY KNOWLEDGE AND ITS APPLICATIONS

  2007cites this paper
• Near-Synonym Choice in an Intelligent Thesaurus

  2007influential citation
• Corpus statistics approaches to discriminating among near-synonyms

  2007influential citation
• Analyzing and modeling real-world phenomena with complex networks: a survey of applications

  2007cites this paper
• Sentiment and near-synonymy: do they go together?

  2007cites this paper
• Understanding Latent Semantic Indexing: A Topological Structure Analysis Using Q-Analysis Method

  2007cites this paper
• A statistical model for near-synonym choice

  2007cites this paper
• Exploring Approaches to Discriminating among Near-Synonyms

  2007cites this paper
• HIT: Web based Scoring Method for English Lexical Substitution

  2007cites this paper
• THE FIRST INTERNATIONAL CONFERENCE ON KNOWLEDGE ENGINEERING PRINCIPLES AND TECHNIQUES (KEPT 2007)

  2007cites this paper
• Detection of Interdomain Routing Anomalies Based on Higher-Order Path Analysis

  2006cites this paper
• A framework for understanding Latent Semantic Indexing (LSI) performance

  2006cites this paper
• Link Analysis of Higher-Order Paths in Supervised Learning Datasets

  2006cites this paper
• Distributed Higher Order Text Mining

  2006cites this paper
• Effects of High-Order Co-occurrences on Word Semantic Similarities

  2006cites this paper
• MACHINE LEARNING APPROACH FOR CONTEXT-SENSITIVE ERROR DETECTION

  2005cites this paper
• Corpus-Based Neural Network Method for Explaining Unknown Words by WordNet Senses

  2005cites this paper
• The Statistics of Word Cooccur-rences: Word Pairs and Collocations

  2004cites this paper
• A Framework for Understanding LSI Performance

  2004cites this paper
• Incremental Construction of an Associative Network from a Corpus

  2004cites this paper
• Lexical knowledge representation with contextonyms

  2003cites this paper
• Query Expansion with Long-Span Collocates

  2003cites this paper
• Suregen-2: a shell system for the generation of clinical documents

  2003cites this paper
• Transitivity and the Co-occurrence Relation in LSI April

  2002cites this paper
• Detecting Patterns in the LSI Term-Term Matrix

  2002cites this paper
• An ATMS-based architecture for stylistics-aware text generation

  2002cites this paper
• A Mathematical View of Latent Semantic Indexing: Tracing Term Co-occurrences

  2002cites this paper
• Improving Retrieval Performance with Positive and Negative Equivalence Classes of Terms

  2002cites this paper