Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference

Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference
复制标题

TextGraphs 2019 共享任务上的推理链:通过事实链进行推理以实现可解释的多跳推理

DOI:
10.18653/v1/d19-5313
复制
发表时间:
2019
期刊:
--
影响因子:
--
通讯作者:
A. McCallum
A. McCallum
中科院分区:
--
文献类型:
--
作者:
Rajarshi Das;Ameya Godbole;M. Zaheer;S. Dhuliawala;A. McCallum

文献摘要

参考文献

被引文献

相似文献

本文描述了我们在EMNLP 2019(Jansen和Ustalov,2019)的TextGraphs研讨会上提交的关于“多跳推理解释再生”的共享任务。我们的系统识别相关的事实链,以解释一个基本的科学考试问题的答案。为了解决“虚假链”导致“语义漂移”的问题,我们训练了一个排名器,该排名器使用事实的上下文表示来为其解释问题答案的相关性打分。我们的系统在平均精度(MAP)指标上排名第一,比第二好的系统高出14.95分。
This paper describes our submission to the shared task on “Multi-hop Inference Explanation Regeneration” in TextGraphs workshop at EMNLP 2019 (Jansen and Ustalov, 2019). Our system identifies chains of facts relevant to explain an answer to an elementary science examination question. To counter the problem of ‘spurious chains’ leading to ‘semantic drifts’, we train a ranker that uses contextualized representation of facts to score its relevance for explaining an answer to a question. Our system was ranked first w.r.t the mean average precision (MAP) metric outperforming the second best system by 14.95 points.
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