Extractive and Abstractive Sentence Labelling of Sentiment-bearing Topics
Extractive and Abstractive Sentence Labelling of Sentiment-bearing Topics
复制标题
DOI：
--
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
M. Barawi;Chenghua Lin;Advaith Siddharthan;Yinbing Liu
中科院分区：
文献类型：
--
作者：
M. Barawi;Chenghua Lin;Advaith Siddharthan;Yinbing Liu
本文研究了用描述性句子标签自动标注带有情感的主题的问题。我们提出解决这个问题的两种方法，一种是抽象的，另一种是抽象的。这两种方法都依赖于一种新的机制来自动学习语料库中每个句子与从语料库中提取的带有情感的主题的相关性。提取方法使用句子排序算法进行标签选择，该算法首次联合优化主题-句子相关性和方面-情感共同覆盖。抽象方法通过使用句子融合来生成包含多个句子相关内容的句子标签，从而解决了方面-情感共覆盖问题。据我们所知，我们是第一个研究标记带有情感的主题问题的人。我们在三个真实数据集上的实验结果表明，在促进主题理解和解释方面，抽取和抽象方法都优于四个强基线。此外，当比较抽取标签和抽象标签时，在相同的标签长度约束下，抽象标签能够提供更多的主题信息覆盖。尽管其语法分数比完全提取的人工句子平均低16%，但抽象融合生成的主题标签可以合成包含情感的主题解释所需的丰富信息。
This paper tackles the problem of automatically labelling sentiment-bearing topics with descriptive sentence labels. We propose two approaches to the problem, one extractive and the other abstractive. Both approaches rely on a novel mechanism to automatically learn the relevance of each sentence in a corpus to sentiment-bearing topics extracted from that corpus. The extractive approach uses a sentence ranking algorithm for label selection which for the first time jointly optimises topic–sentence relevance as well as aspect–sentiment co-coverage. The abstractive approach instead addresses aspect–sentiment co-coverage by using sentence fusion to generate a sentential label that includes relevant content from multiple sentences. To our knowledge, we are the first to study the problem of labelling sentiment-bearing topics. Our experimental results on three real-world datasets show that both the extractive and abstractive approaches outperform four strong baselines in terms of facilitating topic understanding and interpretation. In addition, when comparing extractive and abstractive labels, abstractive labels are able to provide more topic information coverage given the same label length constraint. Despite having 16% average on grammatical scores below fully extracted human-written sentences, the abstractive fusion generates topic labels can synthesise rich information needed for sentiment-bearing topic interpretations.