Browse State-of-the-Art › Word Sense Induction

Word Sense Induction

19 papers with code · 1 benchmark · 1 dataset archive 2025-07-28

Natural Language Processing

Word sense induction (WSI) is widely known as the “unsupervised version” of WSD. The problem states as: Given a target word (e.g., “cold”) and a collection of sentences (e.g., “I caught a cold”, “The weather is cold”) that use the word, cluster the sentences according to their different senses/meanings. We do not need to know the sense/meaning of each cluster, but sentences inside a cluster should have used the target words with the same sense.

Description from NLP Progress

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
SemEval 2010 WSI (5 rows) BERT+DP Towards better substitution-based word sense induction code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 107 · with a code link: 19 · where Syntology ran a sample: 1 (0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 107 tagged: 0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 107, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 25 Feb 2015 3 repositories listed
    Recently proposed Skip-gram model is a powerful method for learning high-dimensional word representations that capture rich semantic relationships between words.
  • 28 Sep 2022 2 repositories listed
    We present RuDSI, a new benchmark for word sense induction (WSI) in Russian.
  • 29 May 2019 2 repositories listed
    Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses.
  • 6 Jul 2017 2 repositories listed
    Evaluating these methods is also problematic, as rigorous quantitative evaluations in this space is limited, especially when compared with single-sense embeddings.
  • 19 Feb 2024 1 repository listed
    Our evaluation is performed across different languages on eight available benchmarks for LSC, and shows that (i) APD outperforms other approaches for GCD; (ii) XL-LEXEME outperforms other contextualized models for WiC…
  • 19 Dec 2022 1 repository listed
    Scholarly text is often laden with jargon, or specialized language that can facilitate efficient in-group communication within fields but hinder understanding for out-groups.
  • 7 Jun 2022 1 repository listed
    Lexical substitution, i. e. generation of plausible words that can replace a particular target word in a given context, is an extremely powerful technology that can be used as a backbone of various NLP applications…
  • 25 Jan 2021 1 repository listed
    To avoid the "meaning conflation deficiency" of word embeddings, a number of models have aimed to embed individual word senses.
  • 1 Nov 2020 1 repository listed
    The task of Diachronic Word Sense Induction (DWSI) aims to identify the meaning of words from their context, taking the temporal dimension into account.
  • 1 Nov 2020 1 repository listed
    The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks.
  • 18 Oct 2020 1 repository listed
    Much as the social landscape in which languages are spoken shifts, language too evolves to suit the needs of its users.
  • 22 Nov 2018 1 repository listed
    Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics…
  • 26 Aug 2018 1 repository listed
    An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors.
  • 6 May 2018 1 repository listed
    The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE-2018).
  • 1 Jul 2017 1 repository listed
    The key idea is to utilize word sememes to capture exact meanings of a word within specific contexts accurately.
  • 24 Apr 2017 1 repository listed
    This paper presents a new graph-based approach that induces synsets using synonymy dictionaries and word embeddings.
  • 1 Apr 2017 1 repository listed
    To evaluate our method we construct two 600-word testsets for word-to-synset matching in French and Russian using native speakers and evaluate the performance of our method along with several other recent approaches.
  • 1 Jun 2013 1 repository listed
  • 1 Jul 2012 1 repository listed
  • Polysemy and synonymy are two crucial interrelated facets of lexical ambiguity.
  • Multilingual Substitution-based Word Sense Induction
    17 May 2024 0 repositories listed
    Word Sense Induction (WSI) is the task of discovering senses of an ambiguous word by grouping usages of this word into clusters corresponding to these senses.
  • The LSCD Benchmark: a Testbed for Diachronic Word Meaning Tasks
    29 Mar 2024 0 repositories listed
    Lexical Semantic Change Detection (LSCD) is a complex, lemma-level task, which is usually operationalized based on two subsequently applied usage-level tasks: First, Word-in-Context (WiC) labels are derived for pairs of…
  • Word Sense Induction with Knowledge Distillation from BERT
    20 Apr 2023 0 repositories listed
    Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems.
  • Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization
    11 Oct 2022 0 repositories listed
    Word sense induction (WSI) is a difficult problem in natural language processing that involves the unsupervised automatic detection of a word's senses (i.e. meanings).
  • Absinth: A small world approach to word sense induction
    1 Sep 2022 0 repositories listed
  • Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings
    7 Apr 2022 0 repositories listed
    Wordnets are indispensable tools for various natural language processing applications.
  • Topological Data Analysis for Word Sense Disambiguation
    1 Mar 2022 0 repositories listed
    We develop and test a novel unsupervised algorithm for word sense induction and disambiguation which uses topological data analysis.
  • Word Sense Induction with Attentive Context Clustering
    1 Dec 2021 0 repositories listed
    In this paper, we present ACCWSI (Attentive Context Clustering WSI), a method for Word Sense Induction, suitable for languages with limited resources.
  • Large Scale Substitution-based Word Sense Induction
    14 Oct 2021 0 repositories listed
    We present a word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora.
  • BOS at SemEval-2020 Task 1: Word Sense Induction via Lexical Substitution for Lexical Semantic Change Detection
    1 Dec 2020 0 repositories listed
    SemEval-2020 Task 1 is devoted to detection of changes in word meaning over time.
  • Topology of Word Embeddings: Singularities Reflect Polysemy
    18 Nov 2020 0 repositories listed
  • Combining Neural Language Models for WordSense Induction
    23 Jun 2020 0 repositories listed
  • A Comparative Study of Lexical Substitution Approaches based on Neural Language Models
    29 May 2020 0 repositories listed
  • Combining Lexical Substitutes in Neural Word Sense Induction
    1 Sep 2019 0 repositories listed
  • Using Wiktionary as a resource for WSD : the case of French verbs
    1 May 2019 0 repositories listed
  • Vector representations of text data in deep learning
    7 Jan 2019 0 repositories listed
  • Word Sense Induction using Knowledge Embeddings
    23 Oct 2018 0 repositories listed
  • Disambiguated skip-gram model
    1 Oct 2018 0 repositories listed
  • How much does a word weigh? Weighting word embeddings for word sense induction
    23 May 2018 0 repositories listed
  • Retrofitting Word Representations for Unsupervised Sense Aware Word Similarities
    1 May 2018 0 repositories listed
  • 1 May 2018 0 repositories listed
  • Leveraging Lexical Substitutes for Unsupervised Word Sense Induction
    27 Apr 2018 0 repositories listed
  • Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings
    9 Apr 2018 0 repositories listed
  • Word sense induction using word embeddings and community detection in complex networks
    22 Mar 2018 0 repositories listed
  • 15 Mar 2018 0 repositories listed
  • On Modeling Sense Relatedness in Multi-prototype Word Embedding
    1 Nov 2017 0 repositories listed
  • Finding Individual Word Sense Changes and their Delay in Appearance
    1 Sep 2017 0 repositories listed
  • Parsing with Context Embeddings
    1 Aug 2017 0 repositories listed
  • Using Pseudowords for Algorithm Comparison: An Evaluation Framework for Graph-based Word Sense Induction
    1 May 2017 0 repositories listed
  • Supervised and unsupervised approaches to measuring usage similarity
    1 Apr 2017 0 repositories listed
  • Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation
    1 Apr 2017 0 repositories listed
  • Structured Generative Models of Continuous Features for Word Sense Induction
    1 Dec 2016 0 repositories listed
  • Context-Dependent Sense Embedding
    1 Nov 2016 0 repositories listed
  • 1 Aug 2016 0 repositories listed
  • 17 Jun 2016 0 repositories listed
  • Word Sense Clustering and Clusterability
    1 Jun 2016 0 repositories listed
  • Automatic Biomedical Term Polysemy Detection
    1 May 2016 0 repositories listed
  • Graph-Based Induction of Word Senses in Croatian
    1 May 2016 0 repositories listed
  • One Million Sense-Tagged Instances for Word Sense Disambiguation and Induction
    1 Jul 2015 0 repositories listed
  • Duluth: Word Sense Discrimination in the Service of Lexicography
    1 Jun 2015 0 repositories listed
  • Neural context embeddings for automatic discovery of word senses
    1 Jun 2015 0 repositories listed
  • Efficiency in Ambiguity: Two Models of Probabilistic Semantics for Natural Language
    1 Apr 2015 0 repositories listed
  • Navigating the Semantic Horizon using Relative Neighborhood Graphs
    12 Jan 2015 0 repositories listed
  • A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment
    1 Jan 2015 0 repositories listed
  • Word Sense Induction for Machine Translation
    1 Dec 2014 0 repositories listed
  • A Unified Model for Word Sense Representation and Disambiguation
    1 Oct 2014 0 repositories listed
  • Semantic clustering of Russian web search results: possibilities and problems
    4 Sep 2014 0 repositories listed
  • Improved Estimation of Entropy for Evaluation of Word Sense Induction
    1 Sep 2014 0 repositories listed
  • 1 Aug 2014 0 repositories listed
  • Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources
    1 Aug 2014 0 repositories listed
  • 1 Aug 2014 0 repositories listed
  • Word Sense Induction Using Lexical Chain based Hypergraph Model
    1 Aug 2014 0 repositories listed
  • From the Culinary to the Political Meaning of ``quenelle'' : Using Topic Models For Identifying Novel Senses (De la quenelle culinaire à la quenelle politique : identification de changements sémantiques à l'aide des Topic Models) [in French]
    1 Jul 2014 0 repositories listed
  • Word Sense Induction for Lexical Resource Enrichment (Induction de sens pour enrichir des ressources lexicales) [in French]
    1 Jul 2014 0 repositories listed
  • A Sense-Based Translation Model for Statistical Machine Translation
    1 Jun 2014 0 repositories listed
  • WoSIT: A Word Sense Induction Toolkit for Search Result Clustering and Diversification
    1 Jun 2014 0 repositories listed
  • One Sense per Tweeter ... and Other Lexical Semantic Tales of Twitter
    1 Apr 2014 0 repositories listed
  • A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages
    5 Oct 2013 0 repositories listed
  • Naive Bayes Word Sense Induction
    1 Oct 2013 0 repositories listed
  • Capturing Anomalies in the Choice of Content Words in Compositional Distributional Semantic Space
    1 Sep 2013 0 repositories listed
  • Class-based Word Sense Induction for dot-type nominals
    1 Sep 2013 0 repositories listed
  • Mixing in Some Knowledge: Enriched Context Patterns for Bayesian Word Sense Induction
    1 Sep 2013 0 repositories listed
  • Automatic Term Ambiguity Detection
    1 Aug 2013 0 repositories listed
  • Concreteness and Corpora: A Theoretical and Practical Study
    1 Aug 2013 0 repositories listed
  • Cross-lingual WSD for Translation Extraction from Comparable Corpora
    1 Aug 2013 0 repositories listed
  • DKPro WSD: A Generalized UIMA-based Framework for Word Sense Disambiguation
    1 Aug 2013 0 repositories listed
  • Towards Dynamic Word Sense Discrimination with Random Indexing
    1 Aug 2013 0 repositories listed
  • A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages (État de l'art de l'induction de sens: une voie vers la désambiguïsation lexicale pour les langues peu dotées) [in French]
    1 Jun 2013 0 repositories listed
  • AI-KU: Using Substitute Vectors and Co-Occurrence Modeling For Word Sense Induction and Disambiguation
    1 Jun 2013 0 repositories listed
  • Duluth : Word Sense Induction Applied to Web Page Clustering
    1 Jun 2013 0 repositories listed
  • LIMSI : Cross-lingual Word Sense Disambiguation using Translation Sense Clustering
    1 Jun 2013 0 repositories listed
  • Paving the Way to a Large-scale Pseudosense-annotated Dataset
    1 Jun 2013 0 repositories listed
  • SATTY : Word Sense Induction Application in Web Search Clustering
    1 Jun 2013 0 repositories listed
  • SemEval-2013 Task 11: Word Sense Induction and Disambiguation within an End-User Application
    1 Jun 2013 0 repositories listed
  • SemEval-2013 Task 13: Word Sense Induction for Graded and Non-Graded Senses
    1 Jun 2013 0 repositories listed
  • UKP-WSI: UKP Lab Semeval-2013 Task 11 System Description
    1 Jun 2013 0 repositories listed
  • unimelb: Topic Modelling-based Word Sense Induction for Web Snippet Clustering
    1 Jun 2013 0 repositories listed
  • UoS: A Graph-Based System for Graded Word Sense Induction
    1 Jun 2013 0 repositories listed
  • Clustering and Diversifying Web Search Results with Graph-Based Word Sense Induction
    1 Jan 2013 0 repositories listed
  • Unsupervised Estimation of Word Usage Similarity
    1 Dec 2012 0 repositories listed

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections