# MWE as WSD: Solving Multiword Expression Identification with Word Sense Disambiguation

arXiv: https://arxiv.org/abs/2303.06623 · HTML: https://mlsanity.com/paper/2303.06623/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 51 references that are in the map.
- First posted on arXiv 12 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring](https://mlsanity.com/paper/1905.01969/) (2019)
- [Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders](https://mlsanity.com/paper/2005.02590/) (2020)
- [Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment](https://mlsanity.com/paper/2204.03025/) (2022)
- [Comprehensive Supersense Disambiguation of English Prepositions and Possessives](https://mlsanity.com/paper/1805.04905/) (2018)
- [BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets](https://mlsanity.com/paper/2210.12687/) (2022)
- [Lexical Semantic Recognition](https://mlsanity.com/paper/2004.15008/) (2020)
- [Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions](https://mlsanity.com/paper/1902.10667/) (2019)
- [Training Bi-Encoders for Word Sense Disambiguation](https://mlsanity.com/paper/2105.10146/) (2021)
- [Boundary-based MWE segmentation with text partitioning](https://mlsanity.com/paper/1608.02025/) (2016)

## Abstract (arXiv)

Recent approaches to word sense disambiguation (WSD) utilize encodings of the sense gloss (definition), in addition to the input context, to improve performance. In this work we demonstrate that this approach can be adapted for use in multiword expression (MWE) identification by training models which use gloss and context information to filter MWE candidates produced by a rule-based extraction pipeline. Our approach substantially improves precision, outperforming the state-of-the-art in MWE identification on the DiMSUM dataset by up to 1.9 F1 points and achieving competitive results on the PARSEME 1.1 English dataset. Our models also retain most of their WSD performance, showing that a single model can be used for both tasks. Finally, building on similar approaches using Bi-encoders for WSD, we introduce a novel Poly-encoder architecture which improves MWE identification performance.