A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Multi-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first generates unsupervised clusters of sentences as candidate evidence by accounting links between sentences and coverage with the given query. Then, a RoBERTa-based reranker is trained to bring the most representative evidence cluster to the top. We specifically emphasize on the importance ofdoi:10.18653/v1/2021.naacl-main.363 fatcat:sz7dkcxjvfeqdd4k7djur56gvm