.png){kind=icon}
返回
Syntax-Aware Multi-Spans Generation for Reading Comprehension
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2021.3138679.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This 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.
Keyword:
Answer generation
encoder-decoder mechanism
machine reading comprehension
syntactic parsing
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
分享收藏Phosphomimetic Substitution of CytochromecTyrosine 48 Decreases Respiration and Binding to Cardiolipin and Abolishes Ability to Trigger Downstream Caspase Activation.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏
查看更多内容