基于事实陈述融合和对话细分的对话总结的新框架
Mingkai Zhang1, Dan You1, Shouguang Wang1
1School of Information and Electronic Engineering(Sussex Artificial Intelligence Institute), Zhejiang Gongshang University, Hangzhou, Zhejiang Province, China.
本研究介绍了DS-SS,这是一个抽象对话总结的新框架. 它通过融合事实陈述和细分对话来提高事实一致性和信息性.
科学领域:
- 自然语言处理自然语言处理.
- 人工智能的人工智能
- 计算语言学 计算语言学
背景情况:
- 越来越多的对话数据需要有效的总结技术.
- 抽象对话总结旨在生成简洁的摘要,捕捉对话的本质.
- 现有的方法往往难以保持事实一致性,难以捕捉对话的全部上下文.
研究的目的:
- 提出一个新的序列对序列框架,DS-SS (对话总结与事实陈述融合和对话分割),用于抽象的对话总结.
- 通过整合事实陈述和将对话细分为主题一致的单元来增强对话编码.
- 提高生成的对话摘要的事实一致性和信息性.
主要方法:
- 开发了一个新的序列对序列框架 (DS-SS).
- 实现了事实陈述提取和合并到对话编码过程中.
- 集成了一个对话分割器,将对话划分为主题一致的部分.
- 在SAMSum和DialogSum数据集上进行实验.
主要成果:
- 与强大的基线相比,DS-SS框架表现出优异的表现.
- 无论是自动评估指标还是人类评估都证实了该框架的有效性.
- 生成的摘要表现出更好的事实一致性和信息性.
结论:
- 拟议的DS-SS框架有效地解决了抽象对话总结的局限性.
- 融合事实陈述和对话细分是改善总结的关键创新.
- 该框架显示了对现实世界对话总结应用的巨大潜力.
更多相关视频
09:09Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
05:22Dissociation of the Confounding Influences of Expectancy and Integrative Difficulty Residing in Anomalous Sentences in Event-related Potential Studies
Published on: May 9, 2019
相关概念视频
Techniques of Therapeutic Communication II: Focusing, Paraphrasing, and Summarizing
This therapeutic technique can also be used when a patient brings up pertinent information during a health-related conversation. The...
Nuclear Fusion
A helium nucleus has a mass that is 0.7% less than that of four hydrogen nuclei; this lost mass is converted into energy during the fusion. This reaction produces about...
Tagging and Fusion Proteins
SNAREs and Membrane Fusion
SNAREs exist in pairs that symmetrically interact and catalyze the fusion of the lipid bilayers in vesicle and target organelle. v-SNARE in the vesicle membrane are single polypeptide chains that bind to a complementary t-SNARE, composed of 2...
Framing Effects
Lagging Strand Synthesis
