Prompting Contrastive Explanations for Commonsense Reasoning Tasks
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
复制标题
提示常识推理任务的对比解释
DOI：
10.18653/v1/2021.findings-acl.366
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Hannaneh Hajishirzi
中科院分区：
文献类型：
--
作者：
Bhargavi Paranjape;Julian Michael;Marjan Ghazvininejad;Luke Zettlemoyer;Hannaneh Hajishirzi
许多常识推理NLP任务涉及基于通常隐含的知识在问题或提示的一个或多个可能答案之间进行选择。大型的预训练语言模型（PLM）可以在这些任务上实现接近人类的性能，同时提供很少的人类可解释的证据来证明它们使用的基本推理。在这项工作中，我们展示了如何使用这些相同的模型来生成这样的证据：受人类解释的对比性质的启发，我们使用PLM来完成解释提示，根据证明正确答案所需的关键属性（例如，花生通常是咸的，而葡萄干是甜的）来对比替代品。与以前的非对比替代方案相比，这些解释的条件模型决策提高了两个常识推理基准的性能。这些解释也被人类判断为与解决任务更相关，并促进了一种新的方法来评估解释的可信度。
Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit. Large pretrained language models (PLMs) can achieve near-human performance on such tasks, while providing little human-interpretable evidence of the underlying reasoning they use. In this work, we show how to use these same models to generate such evidence: inspired by the contrastive nature of human explanations, we use PLMs to complete explanation prompts which contrast alternatives according to the key attribute(s) required to justify the correct answer (for example, peanuts are usually salty while raisins are sweet). Conditioning model decisions on these explanations improves performance on two commonsense reasoning benchmarks, as compared to previous non-contrastive alternatives. These explanations are also judged by humans to be more relevant for solving the task, and facilitate a novel method to evaluate explanation faithfulfness.
DOI：
10.18653/v1/2020.acl-main.408
发表时间：
2019-11
期刊：
--
影响因子：
--
作者：
Jay DeYoung;Sarthak Jain;Nazneen Rajani;Eric P. Lehman;Caiming Xiong;R. Socher;Byron C. Wallace
通讯作者：
Jay DeYoung;Sarthak Jain;Nazneen Rajani;Eric P. Lehman;Caiming Xiong;R. Socher;Byron C. Wallace
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