Fine-tuning BERT with Focus Words for Explanation Regeneration

Isaiah Onando Mulang’, Jennifer D’Souza, Sören Auer


Abstract
Explanation generation introduced as the world tree corpus (Jansen et al., 2018) is an emerging NLP task involving multi-hop inference for explaining the correct answer in multiple-choice QA. It is a challenging task evidenced by low state-of-the-art performances(below 60% in F-score) demonstrated on the task. Of the state-of-the-art approaches, fine-tuned transformer-based (Vaswani et al., 2017) BERT models have shown great promise toward continued system performance improvements compared with approaches relying on surface-level cues alone that demonstrate performance saturation. In this work, we take a novel direction by addressing a particular linguistic characteristic of the data — we introduce a novel and lightweight focus feature in the transformer-based model and examine task improvements. Our evaluations reveal a significantly positive impact of this lightweight focus feature achieving the highest scores, second only to a significantly computationally intensive system.
Anthology ID:
2020.starsem-1.13
Volume:
Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venues:
*SEM | COLING | SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
125–130
Language:
URL:
https://aclanthology.org/2020.starsem-1.13
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.starsem-1.13.pdf
Data
Worldtree