Abstract
This paper describes N-XKT (Neural encoding based on eXplanatory Knowledge Transfer), a novel method for the automatic transfer of explanatory knowledge through neural encoding mechanisms. We demonstrate that N-XKT is able to improve accuracy and generalization on science Question Answering (QA). Specifically, by leveraging facts from background explanatory knowledge corpora, the N-XKT model shows a clear improvement on zero-shot QA. Furthermore, we show that N-XKT can be fine-tuned on a target QA dataset, enabling faster convergence and more accurate results. A systematic analysis is conducted to quantitatively analyze the performance of the N-XKT model and the impact of different categories of knowledge on the zero-shot generalization task.- Anthology ID:
- 2021.iwcs-1.5
- Volume:
- Proceedings of the 14th International Conference on Computational Semantics (IWCS)
- Month:
- June
- Year:
- 2021
- Address:
- Groningen, The Netherlands (online)
- Editors:
- Sina Zarrieß, Johan Bos, Rik van Noord, Lasha Abzianidze
- Venue:
- IWCS
- SIG:
- SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 38–50
- Language:
- URL:
- https://aclanthology.org/2021.iwcs-1.5
- DOI:
- Cite (ACL):
- Zili Zhou, Marco Valentino, Donal Landers, and André Freitas. 2021. Encoding Explanatory Knowledge for Zero-shot Science Question Answering. In Proceedings of the 14th International Conference on Computational Semantics (IWCS), pages 38–50, Groningen, The Netherlands (online). Association for Computational Linguistics.
- Cite (Informal):
- Encoding Explanatory Knowledge for Zero-shot Science Question Answering (Zhou et al., IWCS 2021)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/2021.iwcs-1.5.pdf
- Data
- ARC (AI2 Reasoning Challenge), OpenBookQA, Worldtree