ESC: Redesigning WSD with Extractive Sense Comprehension

Edoardo Barba, Tommaso Pasini, Roberto Navigli


Abstract
Word Sense Disambiguation (WSD) is a historical NLP task aimed at linking words in contexts to discrete sense inventories and it is usually cast as a multi-label classification task. Recently, several neural approaches have employed sense definitions to better represent word meanings. Yet, these approaches do not observe the input sentence and the sense definition candidates all at once, thus potentially reducing the model performance and generalization power. We cope with this issue by reframing WSD as a span extraction problem — which we called Extractive Sense Comprehension (ESC) — and propose ESCHER, a transformer-based neural architecture for this new formulation. By means of an extensive array of experiments, we show that ESC unleashes the full potential of our model, leading it to outdo all of its competitors and to set a new state of the art on the English WSD task. In the few-shot scenario, ESCHER proves to exploit training data efficiently, attaining the same performance as its closest competitor while relying on almost three times fewer annotations. Furthermore, ESCHER can nimbly combine data annotated with senses from different lexical resources, achieving performances that were previously out of everyone’s reach. The model along with data is available at https://github.com/SapienzaNLP/esc.
Anthology ID:
2021.naacl-main.371
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4661–4672
Language:
URL:
https://aclanthology.org/2021.naacl-main.371
DOI:
10.18653/v1/2021.naacl-main.371
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.371.pdf
Code
 SapienzaNLP/esc
Data
Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison