arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.10032cs.CLcs.AI
收藏

基于领域级成对语义交互的情感分类

Domain-level Pairwise Semantic Interaction for Aspect-Based Sentiment Classification

Zhenxin Wu, Jiazheng Gong, Kecen Guo, Guanye Liang, Qingliang Che, Bo Liu

摘要:

基于情感的情感分类是情感分析中一个非常具有挑战性的子任务,并且存在严重的类不平衡问题。现有方法只对句子进行独立处理,没有考虑句子之间的领域级关系,无法有效解决类不平衡问题。从直观的角度来看,同一领域的句子往往具有高层次的语义联系。它们的高层语义特征之间的相互作用可以迫使模型产生更好的语义表示,更好地发现句子之间的相似性和细微差别。在这一思想的驱动下,我们提出了一个即插即用的成对语义交互(PSI)模块,该模块以成对句子为输入,通过学习两个句子的语义向量来获得交互信息。随后,生成不同的门以有效地突出每个句子的关键语义特征。最后,利用向量间的对抗性交互作用,使两个句子的语义表达更有区别。在四个ABSC数据集上的实验结果表明,在大多数情况下,PSI优于许多有竞争力的最先进的基线,可以显着缓解类不平衡的问题。

英文摘要:

Aspect-based sentiment classification (ABSC) is a very challenging subtask of sentiment analysis (SA) and suffers badly from the class-imbalance. Existing methods only process sentences independently, without considering the domain-level relationship between sentences, and fail to provide effective solutions to the problem of class-imbalance. From an intuitive point of view, sentences in the same domain often have high-level semantic connections. The interaction of their high-level semantic features can force the model to produce better semantic representations, and find the similarities and nuances between sentences better. Driven by this idea, we propose a plug-and-play Pairwise Semantic Interaction (PSI) module, which takes pairwise sentences as input, and obtains interactive information by learning the semantic vectors of the two sentences. Subsequently, different gates are generated to effectively highlight the key semantic features of each sentence. Finally, the adversarial interaction between the vectors is used to make the semantic representation of two sentences more distinguishable. Experimental results on four ABSC datasets show that, in most cases, PSI is superior to many competitive state-of-the-art baselines and can significantly alleviate the problem of class-imbalance.

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。

↑