arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08536cs.CL
收藏

多视角抽象答案摘要

Multi-Perspective Abstractive Answer Summarization

Yale University(耶鲁大学);Facebook AI(脸书人工智能研究院)

Alexander R. Fabbri, Xiaojian Wu, Srini Iyer, Mona Diab

摘要:

社区问答(CQA)论坛,如堆栈溢出和雅虎!答案包含了一个广泛的问题的答案丰富的资源。每个问题线程可以接收大量具有不同视角的答案。多视角答案摘要的目标是生成一个包含答案所有视角的摘要。多视角、抽象的答案摘要的主要障碍是缺乏数据集来为生成这样的摘要提供监督。这项工作介绍了一种新的数据集创建方法,从现有的CQA论坛自动创建多角度,子弹点摘要。该数据集提供的监督训练模型,以内在地生成多视角摘要。此外,为了训练模型在保持多个视角的同时输出更多样化、更忠实的答案摘要,我们提出了一种多奖励优化技术,并结合了一种基于相关性的多任务损失预测。我们的方法表明,与强大的基线相比,通过自动和人工评估来衡量,视角和忠诚度的覆盖率有所提高。

英文摘要:

Community Question Answering (CQA) forums such as Stack Overflow and Yahoo! Answers contain a rich resource of answers to a wide range of questions. Each question thread can receive a large number of answers with different perspectives. The goal of multi-perspective answer summarization is to produce a summary that includes all perspectives of the answer. A major obstacle for multi-perspective, abstractive answer summarization is the absence of a dataset to provide supervision for producing such summaries. This work introduces a novel dataset creation method to automatically create multi-perspective, bullet-point abstractive summaries from an existing CQA forum. Supervision provided by this dataset trains models to inherently produce multi-perspective summaries. Additionally, to train models to output more diverse, faithful answer summaries while retaining multiple perspectives, we propose a multi-reward optimization technique coupled with a sentence-relevance prediction multi-task loss. Our methods demonstrate improved coverage of perspectives and faithfulness as measured by automatic and human evaluations compared to a strong baseline.

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。

↑