EMNLP Findings2020
An Evaluation Method for Diachronic Word Sense Induction
Ashjan Alsulaimani, Erwan Moreau, Carl Vogel
Abstract
The task of Diachronic Word Sense Induction (DWSI) aims to identify the meaning of words from their context, taking the temporal dimension into account. In this paper we propose an evaluation method based on largescale time-stamped annotated biomedical data, and a range of evaluation measures suited to the task. The approach is applied to two recent DWSI systems, thus demonstrating its relevance and providing an in-depth analysis of the models.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Related papers
- Improving Diachronic Word Sense Induction with a Nonparametric Bayesian methodAshjan Alsulaimani, Erwan MoreauACL Findings 2023
- DWUG: A large Resource of Diachronic Word Usage Graphs in Four LanguagesDominik Schlechtweg, Nina Tahmasebi, Simon Hengchen, Haim Dubossarsky et al.EMNLP 2021 · 1 citation
- When Time Makes Sense: A Historically-Aware Approach to Targeted Sense DisambiguationKaspar Beelen, Federico Nanni, Mariona Coll Ardanuy, Kasra Hosseini et al.ACL Findings 2021 · 9 citations
- Word2Fun: Modelling Words as Functions for Diachronic Word RepresentationBenyou Wang, Emanuele Di Buccio, Massimo MelucciNeurIPS 2021 · 6 citations
- More DWUGs: Extending and Evaluating Word Usage Graph Datasets in Multiple LanguagesDominik Schlechtweg, Pierluigi Cassotti, Bill Noble, David Alfter et al.EMNLP 2024 · 2 citations
