arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.02709cs.CL
收藏

基于注意力的LSTM-CRF网络的特定观点表达抽取

Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network

Indian Institute of Technology Delhi(德里印度理工学院);University of Houston(休斯顿大学)

Abhishek Laddha, Arjun Mukherjee

摘要:

意见短语抽取是细粒度情感分析的关键任务之一。虽然意见表达可以是一般的主观表达,但体特定意见表达既包含体,也包含原始句子上下文中的意见表达。在这项工作中,我们制定的任务作为一个实例的令牌级序列标签。当句子中存在多个方面时,意见短语边界的检测变得困难,并且每个词的标签不仅取决于周围的词,而且还取决于所关注的方面。我们提出了一种具有双向LSTM(Bi-LSTM)和新型注意力机制的神经网络架构。Bi-LSTM层学习单词之间的各种顺序模式,而不需要任何手工制作的功能。注意力机制通过基于位置和内容的存储器捕获当多个方面存在于句子中时上下文词对特定方面意见表达的重要性。在最后一层中加入了条件随机场(CRF)模型,以显式地对输出标签之间的依赖关系进行建模。在www.example.com的酒店数据集上的实验结果表明,我们的方法优于几个最先进的基线。

英文摘要:

Opinion phrase extraction is one of the key tasks in fine-grained sentiment analysis. While opinion expressions could be generic subjective expressions, aspect specific opinion expressions contain both the aspect as well as the opinion expression within the original sentence context. In this work, we formulate the task as an instance of token-level sequence labeling. When multiple aspects are present in a sentence, detection of opinion phrase boundary becomes difficult and label of each word depend not only upon the surrounding words but also with the concerned aspect. We propose a neural network architecture with bidirectional LSTM (Bi-LSTM) and a novel attention mechanism. Bi-LSTM layer learns the various sequential pattern among the words without requiring any hand-crafted features. The attention mechanism captures the importance of context words on a particular aspect opinion expression when multiple aspects are present in a sentence via location and content based memory. A Conditional Random Field (CRF) model is incorporated in the final layer to explicitly model the dependencies among the output labels. Experimental results on Hotel dataset from Tripadvisor.com showed that our approach outperformed several state-of-the-art baselines.

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。

↑