SWING:平衡对话总结的覆盖面和真实性

Kung-Hsiang Huang, Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Wei Xiao, Nicholas Dingwall, William Yang Wang, K. McKeown
{"title":"SWING:平衡对话总结的覆盖面和真实性","authors":"Kung-Hsiang Huang, Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Wei Xiao, Nicholas Dingwall, William Yang Wang, K. McKeown","doi":"10.48550/arXiv.2301.10483","DOIUrl":null,"url":null,"abstract":"Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries. To address this issue, we propose to utilize natural language inference (NLI) models to improve coverage while avoiding introducing factual inconsistencies. Specifically, we use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered, as well as to distinguish between factually consistent and inconsistent generated sentences. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach in balancing coverage and faithfulness, validated with automatic metrics and human evaluations. Additionally, we compute the correlation between commonly used automatic metrics with human judgments in terms of three different dimensions regarding coverage and factual consistency to provide insight into the most suitable metric for evaluating dialogue summaries.","PeriodicalId":73025,"journal":{"name":"Findings (Sydney (N.S.W.)","volume":"1 1","pages":"512-525"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"SWING: Balancing Coverage and Faithfulness for Dialogue Summarization\",\"authors\":\"Kung-Hsiang Huang, Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Wei Xiao, Nicholas Dingwall, William Yang Wang, K. McKeown\",\"doi\":\"10.48550/arXiv.2301.10483\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries. To address this issue, we propose to utilize natural language inference (NLI) models to improve coverage while avoiding introducing factual inconsistencies. Specifically, we use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered, as well as to distinguish between factually consistent and inconsistent generated sentences. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach in balancing coverage and faithfulness, validated with automatic metrics and human evaluations. Additionally, we compute the correlation between commonly used automatic metrics with human judgments in terms of three different dimensions regarding coverage and factual consistency to provide insight into the most suitable metric for evaluating dialogue summaries.\",\"PeriodicalId\":73025,\"journal\":{\"name\":\"Findings (Sydney (N.S.W.)\",\"volume\":\"1 1\",\"pages\":\"512-525\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Findings (Sydney (N.S.W.)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2301.10483\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Findings (Sydney (N.S.W.)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2301.10483","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

缺少信息是对话摘要的一个常见问题,其中引用摘要中的一些信息没有包含在生成的摘要中。为了解决这个问题,我们建议利用自然语言推理(NLI)模型来提高覆盖率,同时避免引入事实不一致。具体来说,我们使用NLI来计算细粒度的训练信号,以鼓励模型在参考摘要中生成未被覆盖的内容,以及区分事实一致和不一致生成的句子。在DialogSum和SAMSum数据集上的实验证实了所提出的方法在平衡覆盖率和可信度方面的有效性,并通过自动度量和人工评估进行了验证。此外,我们根据关于覆盖率和事实一致性的三个不同维度,计算常用的自动度量与人类判断之间的相关性,以深入了解评估对话摘要的最合适度量。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization
Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries. To address this issue, we propose to utilize natural language inference (NLI) models to improve coverage while avoiding introducing factual inconsistencies. Specifically, we use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered, as well as to distinguish between factually consistent and inconsistent generated sentences. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach in balancing coverage and faithfulness, validated with automatic metrics and human evaluations. Additionally, we compute the correlation between commonly used automatic metrics with human judgments in terms of three different dimensions regarding coverage and factual consistency to provide insight into the most suitable metric for evaluating dialogue summaries.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
审稿时长
4 weeks
期刊最新文献
Exploring Pedestrian Injury Severity by Incorporating Spatial Information in Machine Learning Darkness and Death in the U.S.: Walking Distances Across the Nation by Time of Day and Time of Year Activity Reduction as Resilience Indicator: Evidence with Filomena Data The Lifestyle and Mobility Connection of Community Supported Agriculture (CSA) Users Transit Fleet Electrification Barriers, Resolutions and Costs
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1