PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction
PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction
复制标题
DOI：
10.18653/v1/2021.emnlp-main.731
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Rajdeep Mukherjee;Tapas Nayak;Yash Butala;Sourangshu Bhattacharya;Pawan Goyal
中科院分区：
文献类型：
--
作者：
Rajdeep Mukherjee;Tapas Nayak;Yash Butala;Sourangshu Bhattacharya;Pawan Goyal
方面情感三元抽取（ASTE）处理意见三元抽取，包括意见目标或方面、与其相关的情绪以及解释情绪背后基本原理的相应意见术语/范围。现有的研究主要是基于标记的。在采用序列标记方法的方法中，有些方法无法捕捉到三个意见因素之间的强烈相互依赖性，而另一些方法则无法识别具有重叠方面/意见范围的三胞胎。另一方面，最近的网格标记方法在预测方面-意见对之间的情感时未能捕获跨越级语义。与这些不同的是，我们提出了一个无标记的解决方案，同时解决了现有作品的局限性。我们采用了一种编码器-解码器架构，使用基于指针网络的解码框架，该框架在每个时间步骤生成一个完整的意见三元组，从而使我们的解决方案端到端。解码器通过考虑它们的整个检测范围来有效地捕获方面和观点之间的相互作用，同时预测它们的连接情绪。在几个基准数据集上进行的大量实验表明，我们提出的方法具有更好的功效，特别是在召回率方面，以及在预测来自同一评论句子的多个和方面/意见重叠的三联体方面。我们报告了使用和不使用BERT的结果，并演示了特定领域的BERT在任务训练后的效用。
Aspect Sentiment Triplet Extraction (ASTE) deals with extracting opinion triplets, consisting of an opinion target or aspect, its associated sentiment, and the corresponding opinion term/span explaining the rationale behind the sentiment. Existing research efforts are majorly tagging-based. Among the methods taking a sequence tagging approach, some fail to capture the strong interdependence between the three opinion factors, whereas others fall short of identifying triplets with overlapping aspect/opinion spans. A recent grid tagging approach on the other hand fails to capture the span-level semantics while predicting the sentiment between an aspect-opinion pair. Different from these, we present a tagging-free solution for the task, while addressing the limitations of the existing works. We adapt an encoder-decoder architecture with a Pointer Network-based decoding framework that generates an entire opinion triplet at each time step thereby making our solution end-to-end. Interactions between the aspects and opinions are effectively captured by the decoder by considering their entire detected spans while predicting their connecting sentiment. Extensive experiments on several benchmark datasets establish the better efficacy of our proposed approach, especially in recall, and in predicting multiple and aspect/opinion-overlapped triplets from the same review sentence. We report our results both with and without BERT and also demonstrate the utility of domain-specific BERT post-training for the task.