arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.09830cs.CLcs.AI
收藏

基于句法依赖与语义一致性的否定三元组抽取

Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency

School of Data Science, Fudan University(复旦大学数据科学学院);East China University of Science and Technology(华东理工大学);Meituan(美团)

Yuchen Shi, Deqing Yang, Jingping Liu, Yanghua Xiao, Zongyu Wang, Huimin Xu

AI总结:

针对现有否定理解未识别否定主体的问题,提出否定三元组抽取任务,构建融合句法依赖与语义一致性的SSENE模型及NegComment数据集,性能优于基线。

摘要:

以往的否定理解研究主要聚焦于否定触发词检测与否定范围解析,未识别对下游任务同样重要的否定主体。本文提出一项新的否定三元组抽取(NTE)任务,旨在同时抽取否定主体、否定触发词与否定范围。为实现该任务,我们设计了一种全新的句法与语义增强否定抽取模型,名为SSENE,该模型基于编码器-解码器架构的生成式预训练语言模型(PLM)构建,采用多任务学习框架。具体而言,我们将给定句子的句法依赖树融入PLM的编码器,以挖掘否定主体、触发词与范围之间的关联。此外,通过辅助任务学习保障句子与抽取三元组之间的语义一致性。我们还基于美团真实平台的用户评论构建了高质量中文数据集NegComment,在该数据集上的评估显示,与基线模型相比,SSENE取得了最优的NTE性能。消融实验与案例分析也表明,融入句法信息有助于PLM识别主体与触发词之间的长距离依赖关系,而辅助任务学习有助于抽取语义一致性更强的否定三元组。

英文摘要:

Previous works of negation understanding mainly focus on negation cue detection and scope resolution, without identifying negation subject which is also significant to the downstream tasks. In this paper, we propose a new negation triplet extraction (NTE) task which aims to extract negation subject along with negation cue and scope. To achieve NTE, we devise a novel Syntax&Semantic-Enhanced Negation Extraction model, namely SSENE, which is built based on a generative pretrained language model (PLM) {of Encoder-Decoder architecture} with a multi-task learning framework. Specifically, the given sentence's syntactic dependency tree is incorporated into the PLM's encoder to discover the correlations between the negation subject, cue and scope. Moreover, the semantic consistency between the sentence and the extracted triplet is ensured by an auxiliary task learning. Furthermore, we have constructed a high-quality Chinese dataset NegComment based on the users' reviews from the real-world platform of Meituan, upon which our evaluations show that SSENE achieves the best NTE performance compared to the baselines. Our ablation and case studies also demonstrate that incorporating the syntactic information helps the PLM's recognize the distant dependency between the subject and cue, and the auxiliary task learning is helpful to extract the negation triplets with more semantic consistency.

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。

↑