arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.15837cs.CL
收藏

使用答案选择之间的自然语言关系进行机器理解

Using Natural Language Relations between Answer Choices for Machine Comprehension

Purdue University(普渡大学)

Rajkumar Pujari, Dan Goldwasser

摘要:

在评估阅读理解任务的答案选择时,该问题的其他答案选择以及同一段落相关问题的答案通常提供有价值的信息。在本文中,我们提出了一种方法来利用答案选择之间的自然语言关系,如蕴涵和矛盾,以提高机器理解的性能。我们使用一个独立的问答(QA)系统来执行QA任务和一个自然语言推理(NLI)系统来识别选择对之间的关系。然后,我们进行推理,使用一个基于线性规划(ILP)的关系框架,重新评估的独立QA系统的NLI系统确定的关系光的决定。我们还提出了一个多任务学习模型,学习这两个任务联合。

英文摘要:

When evaluating an answer choice for Reading Comprehension task, other answer choices available for the question and the answers of related questions about the same paragraph often provide valuable information. In this paper, we propose a method to leverage the natural language relations between the answer choices, such as entailment and contradiction, to improve the performance of machine comprehension. We use a stand-alone question answering (QA) system to perform QA task and a Natural Language Inference (NLI) system to identify the relations between the choice pairs. Then we perform inference using an Integer Linear Programming (ILP)-based relational framework to re-evaluate the decisions made by the standalone QA system in light of the relations identified by the NLI system. We also propose a multitask learning model that learns both the tasks jointly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑