LIAAD at SemDeep-5 Challenge: Word-in-Context (WiC)
Computation and Language
2019-06-25 v1 Artificial Intelligence
Abstract
This paper describes the LIAAD system that was ranked second place in the Word-in-Context challenge (WiC) featured in SemDeep-5. Our solution is based on a novel system for Word Sense Disambiguation (WSD) using contextual embeddings and full-inventory sense embeddings. We adapt this WSD system, in a straightforward manner, for the present task of detecting whether the same sense occurs in a pair of sentences. Additionally, we show that our solution is able to achieve competitive performance even without using the provided training or development sets, mitigating potential concerns related to task overfitting
Cite
@article{arxiv.1906.10002,
title = {LIAAD at SemDeep-5 Challenge: Word-in-Context (WiC)},
author = {Daniel Loureiro and Alipio Jorge},
journal= {arXiv preprint arXiv:1906.10002},
year = {2019}
}
Comments
Accepted at the SemDeep-5 Workshop in IJCAI 2019. Code and data: https://github.com/danlou/LMMS