New Experiments in Distributional Representations of Synonymy

Recent work on the problem of detecting synonymy through corpus analysis has used the Test of English as a Foreign Language (TOEFL) as a benchmark. However, this test involves as few as 80 questions, prompting questions regarding the statistical significance of reported results. We overcome this limitation by generating a TOEFL-like test using WordNet, containing thousands of questions and composed only of words occurring with sufficient corpus frequency to support sound distributional comparisons. Experiments with this test lead us to a similarity measure which significantly outperforms the best proposed to date. Analysis suggests that a strength of this measure is its relative robustness against polysemy.

• Publication year

  2005

• Venue

  Conference on Computational Natural Language Learning

• Publication date

  2005-06-29

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1706543.1706548
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Characterising Measures of Lexical Distributional Similarity

  2004cited by this paper
• Combining Independent Modules to Solve Multiple-choice Synonym and Analogy Problems

  2003cited by this paper
• Frequency Estimates for Statistical Word Similarity Measures

  2003cited by this paper
• Discovering word senses from text

  2002cited by this paper
• Vector-based semantic analysis: representing word meanings based on random labels

  2001influential reference
• Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL

  2001cited by this paper
• Book Reviews: WordNet: An Electronic Lexical Database

  1999cited by this paper
• Measures of Distributional Similarity

  1999influential reference
• Information Geometry, Bayesian Inference, Ideal Estimates and Error Decomposition

  1998cited by this paper
• Automatic Retrieval and Clustering of Similar Words

  1998cited by this paper
• A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.

  1997influential reference
• Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity

  1997cited by this paper
• $I$-Divergence Geometry of Probability Distributions and Minimization Problems

  1975cited by this paper
• Mathematical structures of language

  1968cited by this paper

• Modelling Intertextuality with N-gram Embeddings

  2025cites this paper
• Building Static Embeddings from Contextual Ones: Is It Useful for Building Distributional Thesauri?

  2022cites this paper
• Décontextualiser des plongements contextuels pour construire des thésaurus distributionnels (Decontextualizing contextual embeddings for building distributional thesauri )

  2022cites this paper
• Paraphrase type identification for plagiarism detection using contexts and word embeddings

  2021cites this paper
• Building and Comparing Lemma Embeddings for Latin. Classical Latin versus Thomas Aquinas

  2020cites this paper
• Asymmetric Attributional Word Similarity Measures to Detect the Relations of Textual Generality

  2020cites this paper
• Word Representation

  2020cites this paper
• Unsupervised Compositionality Prediction of Nominal Compounds

  2019cites this paper
• Extracting and Learning Semantics from Social Web Data

  2019cites this paper
• Vir is to Moderatus as Mulier is to Intemperans - Lemma Embeddings for Latin

  2019cites this paper
• Wordnet-based Evaluation of Large Distributional Models for Polish

  2018cites this paper
• Application of Text Analytics to Extract and Analyze Material–Application Pairs from a Large Scientific Corpus

  2018cites this paper
• A Survey on Portuguese Lexical Knowledge Bases: Contents, Comparison and Combination

  2018cites this paper
• Knowing the Author by the Company His Words Keep

  2018cites this paper
• Comparing and Combining Portuguese Lexical-Semantic Knowledge Bases

  2017cites this paper
• Extending Thesauri Using Word Embeddings and the Intersection Method

  2017cites this paper
• Distributional models of multiword expression compositionality prediction

  2017cites this paper
• Compositional Semantics using Feature-Based Models from WordNet

  2017cites this paper
• Pattern-based methods for Improved Lexical Semantics and Word Embeddings

  2017cites this paper
• Turkish synonym identification from multiple resources: monolingual corpus, mono/bilingual online dictionaries, and WordNet

  2017cites this paper
• B2SG: a TOEFL-like Task for Portuguese

  2016influential citation
• The Portuguese B ^2 2 SG: A Semantic Test for Distributional Thesaurus

  2016cites this paper
• Comparing explicit and predictive distributional semantic models endowed with syntactic contexts

  2016cites this paper
• Data-driven natural language generation using statistical machine translation and discriminative learning. (L'approche discriminante à la génération de la parole)

  2016cites this paper
• Predicting the Compositionality of Nominal Compounds: Giving Word Embeddings a Hard Time

  2016cites this paper
• Automatic Corpus Extension for Data-driven Natural Language Generation

  2016cites this paper
• Specializing Word Embeddings for Similarity or Relatedness

  2015cites this paper
• Réordonnancer des thésaurus distributionnels en combinant différents critères [Reorder distributional thesauri by combining different criteria]

  2015cites this paper
• Sparsity and normalization in word similarity systems

  2015cites this paper
• Tesauros Distribucionais para o Português: avaliação de metodologias

  2015influential citation
• Typing Relations in Distributional Thesauri

  2015cites this paper
• Nothing like Good Old Frequency: Studying Context Filters for Distributional Thesauri

  2014influential citation
• On the effect of word frequency on distributional similarity

  2014cites this paper
• Exploring the neighbor graph to improve distributional thesauri (Explorer le graphe de voisinage pour améliorer les thésaurus distributionnels) [in French]

  2014cites this paper
• Improving sparse word similarity models with asymmetric measures

  2014cites this paper
• Improving distributional thesauri by exploring the graph of neighbors

  2014cites this paper
• Calculating semantic relatedness for biomedical use in a knowledge-poor environment

  2014cites this paper
• Comparing Similarity Measures for Distributional Thesauri

  2014influential citation
• Partial Measure of Semantic Relatedness Based on the Local Feature Selection

  2014cites this paper
• Predicting the relevance of distributional semantic similarity with contextual information

  2014cites this paper
• Compounds and distributional thesauri

  2014influential citation
• An Integrated Approach to Automatic Synonym Detection in Turkish Corpus

  2014cites this paper
• Unsupervised selection of semantic relations for improving a distributional thesaurus (Sélection non supervisée de relations sémantiques pour améliorer un thésaurus distributionnel) [in French]

  2013cites this paper
• Identifying Bad Semantic Neighbors for Improving Distributional Thesauri

  2013cites this paper
• Discovery of noun semantic relations based on sentential context analysis

  2013influential citation
• Asymmetric Distributional Similarity Measures to Recognize Textual Entailment by Generality. (Mesures de similarité distributionnelle asymétrique pour la détection de l'implication textuelle par généralité)

  2013cites this paper
• Disambiguating implicit temporal queries for temporal information retrieval applications

  2013cites this paper
• Lexical Acquisition for Clinical Text Mining Using Distributional Similarity

  2012cites this paper
• Enriching temporal query understanding through date identification: how to tag implicit temporal queries?

  2012cites this paper
• GTE: a distributional second-order co-occurrence approach to improve the identification of top relevant dates in web snippets

  2012cites this paper
• Distributional Semantics Approach to Detecting Synonyms in Croatian Language

  2012influential citation
• Combining Bootstrapping and Feature Selection for Improving a Distributional Thesaurus

  2012cites this paper
• Exploring the Semantic Meaning of Constructs that Lead to Human Decisions

  2011cites this paper
• Comparaison d’une approche miroir et d’une approche distributionnelle pour l’extraction de mots sémantiquement reliés (Comparing a mirror approach and a distributional approach for extracting semantically related words)

  2011cites this paper
• Exploring patterns in dictionary definitions for synonym extraction

  2011cites this paper
• Comparing Distributional and Mirror Translation Similarities for Extracting Synonyms

  2011cites this paper
• Automatic discovery of word semantic relations using paraphrase alignment and distributional lexical semantics analysis

  2010influential citation
• Discovery of numerous specific topics via term co-occurrence analysis

  2010cites this paper
• Paraphrase Alignment for Synonym Evidence Discovery

  2010cites this paper
• Parallel, massive processing in SuperMatrix—A general tool for distributional semantic analysis of corpus

  2010cites this paper
• Testing Semantic Similarity Measures for Extracting Synonyms from a Corpus

  2010influential citation
• Simmered Greedy Optimization for Co-clustering

  2010cites this paper
• Extraction of Polish noun senses from large corpora by means of clustering

  2010cites this paper
• Similarité sémantique et extraction de synonymes à partir de corpus

  2010cites this paper
• Morphosyntactic Constraints in the Acquisition of Linguistic Knowledge for Polish

  2009cites this paper
• A Wordnet from the ground up

  2009cites this paper
• Extracting Synonyms from Dictionary Definitions

  2009cites this paper
• Relieving Polysemy Problem for Synonymy Detection

  2009influential citation
• Normalized Web Distance and Word Similarity

  2009cites this paper
• Extracting Synonyms from Dictionary Definitions

  2009cites this paper
• Rank-Based Transformation in Measuring Semantic Relatedness

  2009cites this paper
• Sense-based clustering of Polish nouns in the extraction of semantic relatedness

  2008cites this paper
• SuperMatrix: a General tool for lexical semantic knowledge acquisition

  2008influential citation
• Words, Concepts and Relations in the Construction of Polish WordNet

  2008cites this paper
• Towards semi-automatic extraction of lexical semantics relations for Polish

  2008influential citation
• The XTREEM Methods for Ontology Learning from Web Documents

  2008cites this paper
• Corpus-based Semantic Relatedness for the Construction of Polish WordNet

  2008influential citation
• Mapping nanosciences by citation flows: A preliminary analysis

  2007cites this paper
• Semantic Similarity Measure of Polish Nouns Based on Linguistic Features

  2007influential citation
• Statistical Translation, Heat Kernels and Expected Distances

  2007cites this paper
• Extended Similarity Test for the Evaluation of Semantic SimilarityFunctions

  2007influential citation
• One Sense Per Discourse for Synonym Detection

  2007influential citation
• Automatic Selection of Heterogeneous Syntactic Features in Semantic Similarity of Polish Nouns

  2007cites this paper
• Combination of Global and Local Attributional Similarities for Synonym Detection

  2007cites this paper
• Model Unification in Support of Political Process

  2006cites this paper
• Business Process Interoperability with Living Ontologies

  2006cites this paper
• Synonym Extraction Using a Semantic Distance on a Dictionary

  2006cites this paper
• Using context-window overlapping in synonym discovery and ontology extension

  2005cites this paper