Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
复制标题
DOI：
10.48550/arxiv.2211.07743
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Joseph Peper;Lu Wang
中科院分区：
文献类型：
--
作者：
Joseph Peper;Lu Wang
产生式模型在基于方面的情感分析(ABSA)任务中表现出了令人印象深刻的结果，特别是对于提取方面-类别-观点-情感(ACOS)四元组的新兴任务。然而，这些模型难以处理隐含的情感表达，这在在线评论等固执己见的内容中常见。在这项工作中，我们介绍了Gen-SCL-NAT，它由两种改进的结构化生成技术组成，用于ACOS四重提取。首先，我们提出了Gen-SCL，这是一个有监督的对比学习目标，通过鼓励模型产生可跨关键输入属性(如情感极性和隐含观点和方面的存在)区分的输入表示，来帮助四倍预测。其次，我们引入了Gen-NAT，这是一种新的结构化生成格式，它更好地适应了自回归编解码器模型，以生成式的方式提取四元组。实验结果表明，Gen-SCL-NAT在三个ACOS数据集上取得了最好的性能，F1平均提高了1.48%，其中在Laptop-L1数据集上最大提高了1.73%。此外，我们看到在隐含方面和意见分歧方面取得了显著进展，这已经被证明是对现有ACOS方法的挑战。
Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples. However, these models struggle with implicit sentiment expressions, which are commonly observed in opinionated content such as online reviews. In this work, we introduce GEN-SCL-NAT, which consists of two techniques for improved structured generation for ACOS quadruple extraction. First, we propose GEN-SCL, a supervised contrastive learning objective that aids quadruple prediction by encouraging the model to produce input representations that are discriminable across key input attributes, such as sentiment polarity and the existence of implicit opinions and aspects. Second, we introduce GEN-NAT, a new structured generation format that better adapts autoregressive encoder-decoder models to extract quadruples in a generative fashion. Experimental results show that GEN-SCL-NAT achieves top performance across three ACOS datasets, averaging 1.48% F1 improvement, with a maximum 1.73% increase on the LAPTOP-L1 dataset. Additionally, we see significant gains on implicit aspect and opinion splits that have been shown as challenging for existing ACOS approaches.