CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
This work addresses generative question answering for review-based datasets, representing an incremental improvement with specific gains in precision and answer quality.
The authors tackled multi-passage generative question answering by proposing CHIME, a cross-passage hierarchical memory network that extends XLNet with memory modules, resulting in outperforming state-of-the-art baselines on the AmazonQA review dataset with better syntactically well-formed answers and increased precision.
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.