paper-with-me

Word Sense Induction

1개 벤치마크 · 논문 108편 · 이 태스크의 논문 보기 →

Benchmarks

SemEval 2010 WSI

결과 10개

Most implemented

Papers

In the LLM era, Word Sense Induction remains unsolved

2026-03-12 · Anna Mosolova, Marie Candito, Carlos Ramisch arxiv

In the absence of sense-annotated data, word sense induction (WSI) is a compelling alternative to word sense disambiguation, particularly in low-resource or domain-specific settings. In this paper, we emphasize methodolo…

Word Sense DisambiguationWord Sense InductionData Augmentation

To Word Senses and Beyond: Inducing Concepts with Contextualized Language Models

2024-06-28 · Bastien Liétard, Pascal Denis, Mikaella Keller

Polysemy and synonymy are two crucial interrelated facets of lexical ambiguity. While both phenomena are widely documented in lexical resources and have been studied extensively in NLP, leading to dedicated systems, they…

ClusteringLEMMAWord Sense Induction

Multilingual Substitution-based Word Sense Induction

2024-05-17 · Denis Kokosinskii, Nikolay Arefyev

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. Many approaches were proposed to solve WSI in English and a f…

Language ModelingLanguage ModellingWord Sense Induction

The LSCD Benchmark: a Testbed for Diachronic Word Meaning Tasks

2024-03-29 · Dominik Schlechtweg, Shafqat Mumtaz Virk, Nikolay Arefyev

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 …

Change DetectionLEMMAModel OptimizationWord Sense Induction

A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change

2024-02-19 · Francesco Periti, Nina Tahmasebi

Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison …

Change DetectionWord EmbeddingsWord Sense Induction

Word Sense Induction with Knowledge Distillation from BERT

2023-04-20 · Anik Saha, Alex Gittens, Bulent Yener

Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these …

Knowledge DistillationLanguage ModelingLanguage ModellingWord Embeddings+2

전체 108편 보기 →