计算机科学
判决
人工智能
序列(生物学)
自然语言处理
情绪分析
任务(项目管理)
遗传学
管理
经济
生物
作者
Yaxin Liu,Yan Zhou,Ziming Li,Junlin Wang,Wei Zhou,Songlin Hu
出处
期刊:IEEE/ACM transactions on audio, speech, and language processing
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:31: 2272-2285
被引量:4
标识
DOI:10.1109/taslp.2023.3282379
摘要
Aspect Sentiment Triplet Extraction (ASTE) is an emerging task of fine-grained sentiment analysis, which aims to extract aspect terms, associated opinion terms, and sentiment polarities in the form of triplets. Thus, ASTE involves two groups of subtasks: aspect/opinion term extraction and aspect-opinion-pair sentiment classification. Due to the high correlations of subtasks, three categories of joint methods have been proposed, including end-to-end tagging-based methods , cascaded span-based methods , and sequence-to-sequence generation-based methods . These methods basically learn either a shared feature space or a shared sentence encoder to capture interactions across all subtasks by parameter sharing. However, they fail to learn deep and mutual interactive features for ASTE. In this work, we present a novel tagging scheme to cast ASTE as a unified boundary-words relation classification problem. Subsequently, we propose an end-to-end Hierarchical Interaction Model (HIM), exploiting deep and mutual interactions across subtasks mainly with two interaction modules. The first-level interaction module primarily leverages multi-task learning models to capture implicit subtask interactions. Then, the second-level interaction module, namely Gated Interaction Network (GIN), adopts a novel gated control mechanism and a newly-designed Conditional BiLSTM (Cond-BiLSTM) network to capture explicit subtask interactions. Moreover, to refine the unreliable outputs of the first-level module, we develop a General word-Pair Relationship Learning (G-PRL) component. With the task-shared features as input, G-PRL further facilitates interactions between term extraction and pair classification. We conduct experiments on two benchmarks and achieve promising results. Extensive analyses demonstrate the effectiveness and flexibility of our work.
科研通智能强力驱动
Strongly Powered by AbleSci AI