♫ MuSiQue: Multihop Questions via Single-hop Question Composition

♫ MuSiQue: Multihop Questions via Single-hop Question Composition
复制标题

♫ MuSiQue:通过单跳问题组合提出多跳问题

DOI:
--
复制
发表时间:
2021
影响因子:
10.9
通讯作者:
Ashish Sabharwal
Ashish Sabharwal
中科院分区:
人文科学1区
文献类型:
--
作者:
H. Trivedi;Niranjan Balasubramanian;Tushar Khot;Ashish Sabharwal

文献摘要

参考文献

被引文献

相似文献

由于已知可以通过快捷方式来解决问题,因此多台上的推理仍然是一个目标。系统地选择了连接的单跳问题,也就是说,一个推理步骤非常依赖于另一种底层的信息。针对连接的推理,它对施工过程和最终的K-Hop问题的特性提供了精细的控制现有的数据集,整体上的Musique-ANS更加困难(人类 - 机器人差距3倍),并且很难通过断开的推理作弊(例如,单跳模型在F1中的下降30分)。对比的问题,以产生更严格的数据集,Musique-Full。
Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, requires proper multihop reasoning? To this end, we introduce a bottom–up approach that systematically selects composable pairs of single-hop questions that are connected, that is, where one reasoning step critically relies on information from another. This bottom–up methodology lets us explore a vast space of questions and add stringent filters as well as other mechanisms targeting connected reasoning. It provides fine-grained control over the construction process and the properties of the resulting k-hop questions. We use this methodology to create MuSiQue-Ans, a new multihop QA dataset with 25K 2–4 hop questions. Relative to existing datasets, MuSiQue-Ans is more difficult overall (3× increase in human–machine gap), and harder to cheat via disconnected reasoning (e.g., a single-hop model has a 30-point drop in F1). We further add unanswerable contrast questions to produce a more stringent dataset, MuSiQue-Full. We hope our datasets will help the NLP community develop models that perform genuine multihop reasoning.1
DOI: 10.18653/v1/n19-1405
发表时间: 2019
期刊: --
影响因子: --
作者:
Jifan Chen;Greg Durrett
通讯作者: Jifan Chen;Greg Durrett
DOI: 10.18653/v1/2020.findings-emnlp.117
发表时间: 2020-04
期刊: --
影响因子: --
作者:
Matt Gardner;Yoav Artzi;Jonathan Berant;Ben Bogin;Sihao Chen;Dheeru Dua;Yanai Elazar;Ananth Gottumukkala;Nitish Gupta;Hannaneh Hajishirzi;Gabriel Ilharco;Daniel Khashabi;Kevin Lin;Jiangming Liu;Nelson F. Liu;Phoebe Mulcaire;Qiang Ning;Sameer Singh;Noah A. Smith;Sanjay Subramanian;Eric Wallace;Ally Zhang;Ben Zhou
通讯作者: Matt Gardner;Yoav Artzi;Jonathan Berant;Ben Bogin;Sihao Chen;Dheeru Dua;Yanai Elazar;Ananth Gottumukkala;Nitish Gupta;Hannaneh Hajishirzi;Gabriel Ilharco;Daniel Khashabi;Kevin Lin;Jiangming Liu;Nelson F. Liu;Phoebe Mulcaire;Qiang Ning;Sameer Singh;Noah A. Smith;Sanjay Subramanian;Eric Wallace;Ally Zhang;Ben Zhou