Abstract | ||
---|---|---|
AbstractThis paper presents a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks whose answers cannot be simply extracted as one span from the given passages. Using a pointer network-style extractive decoder for such type of MRC may result in unsatisfactory performance when the ground-truth answers are given by human annotators or highly re-paraphrased from parts of the passages. On the other hand, using a generative decoder cannot well guarantee the resulted answers with well-formed syntax and semantics when encountering long sentences. Therefore, to alleviate the obvious drawbacks of both sides, we propose an answer making-up method from extracted multi-spans that are learned by our model as highly confident $n$-gram candidates in the given passage. That is, the returned answers are composed of discontinuous multi-spans but not just one consecutive span in the given passages anymore. The proposed method is simple but effective: empirical experiments on MS MARCO show that the proposed method has a better performance on accurately generating long answers and substantially outperforms two typical competitive one-span and Seq2Seq baseline decoders. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TASLP.2021.3138679 | IEEE/ACM Transactions on Audio, Speech and Language Processing |
Keywords | DocType | Volume |
Answer generation, encoder-decoder mechanism, machine reading comprehension, syntactic parsing | Journal | 10.5555 |
Issue | ISSN | Citations |
taslp.2022.issue-30 | 2329-9290 | 0 |
PageRank | References | Authors |
0.34 | 12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhuosheng Zhang | 1 | 57 | 14.93 |
Yiqing Zhang | 2 | 79 | 9.74 |
Hai Zhao | 3 | 960 | 113.64 |