Abstract
We introduce CHIME, a cross-passage hierarchical memory network for question answering (QA) via text generation. It extends XLNet introducing an auxiliary memory module consisting of two components: the context memory collecting cross-passage evidences, and the answer memory working as a buffer continually refining the generated answers. Empirically, we show the efficacy of the proposed architecture in the multi-passage generative QA, outperforming the state-of-the-art baselines with better syntactically well-formed answers and increased precision in addressing the questions of the AmazonQA review dataset. An additional qualitative analysis revealed the interpretability introduced by the memory module.- Anthology ID:
- 2020.coling-main.229
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 2547–2560
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.229
- DOI:
- 10.18653/v1/2020.coling-main.229
- Cite (ACL):
- Junru Lu, Gabriele Pergola, Lin Gui, Binyang Li, and Yulan He. 2020. CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2547–2560, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering (Lu et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.229.pdf
- Code
- LuJunru/CHIME
- Data
- AmazonQA, SQuAD