arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2104.08765cs.CL
收藏

通过自然语言反馈改进神经模型性能

Improving Neural Model Performance through Natural Language Feedback on Their Explanations

Carnegie Mellon University(卡内基梅隆大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所)

Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Yiming Yang, Peter Clark, Keisuke Sakaguchi, Ed Hovy

摘要:

一类用于推理任务的可解释NLP模型通过生成自由形式或结构化解释来支持其决策,但是当这些支持结构包含错误时会发生什么?我们的目标是允许用户通过自然语言反馈交互式地纠正解释结构。我们介绍MERCURIE -一个交互式系统,它通过在自然语言中获得人类反馈来完善对给定推理任务的解释。我们的方法生成的图形,有40%的不一致性相比,现成的系统。此外,简单地将校正后的解释结构附加到输出中,可以在所有三个领域的可废止推理的准确性上获得1.2分。我们在https://tinyurl.com/mercurie上发布了一个由我们的系统生成的超过450 k图的可撤销推理数据集。

英文摘要:

A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors? Our goal is to allow users to interactively correct explanation structures through natural language feedback. We introduce MERCURIE - an interactive system that refines its explanations for a given reasoning task by getting human feedback in natural language. Our approach generates graphs that have 40% fewer inconsistencies as compared with the off-the-shelf system. Further, simply appending the corrected explanation structures to the output leads to a gain of 1.2 points on accuracy on defeasible reasoning across all three domains. We release a dataset of over 450k graphs for defeasible reasoning generated by our system at https://tinyurl.com/mercurie .

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。

↑