Name
Abstract | ||
|---|---|---|
Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR. |
Year | Venue | DocType |
|---|---|---|
2021 | NAACL-HLT | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chen Zhao | 1 | 7 | 0.76 |
| Chen-Yan Xiong | 2 | 405 | 30.82 |
| Jordan Boyd-Graber | 3 | 1420 | 84.60 |
| Hal Daumé, III | 4 | 3673 | 200.05 |