SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction

Aspect terms extraction and opinion terms extraction are two key problems of fine-grained Aspect Based Sentiment Analysis (ABSA). The aspect-opinion pairs can provide a global profile about a product or service for consumers and opinion mining systems. However, traditional methods can not directly output aspect-opinion pairs without given aspect terms or opinion terms. Although some recent co-extraction methods have been proposed to extract both terms jointly, they fail to extract them as pairs. To this end, this paper proposes an end-to-end method to solve the task of Pair-wise Aspect and Opinion Terms Extraction (PAOTE). Furthermore, this paper treats the problem from a perspective of joint term and relation extraction rather than under the sequence tagging formulation performed in most prior works. We propose a multi-task learning framework based on shared spans, where the terms are extracted under the supervision of span boundaries. Meanwhile, the pair-wise relations are jointly identified using the span representations. Extensive experiments show that our model consistently outperforms state-of-the-art methods.

[1]  Jun Zhao,et al.  Opinion Target Extraction Using Word-Based Translation Model , 2012, EMNLP.

[2]  Makoto Miwa,et al.  Modeling Joint Entity and Relation Extraction with Table Representation , 2014, EMNLP.

[3]  Xiaojun Wan,et al.  Attention-based LSTM Network for Cross-Lingual Sentiment Classification , 2016, EMNLP.

[4]  Zhen Huang,et al.  Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification , 2019, ACL.

[5]  Oren Etzioni,et al.  Extracting Product Features and Opinions from Reviews , 2005, HLT.

[6]  Chun Chen,et al.  Opinion Word Expansion and Target Extraction through Double Propagation , 2011, CL.

[7]  Xiaokui Xiao,et al.  Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms , 2017, AAAI.

[8]  Hao Yu,et al.  Structure-Aware Review Mining and Summarization , 2010, COLING.

[9]  Chris Develder,et al.  Joint entity recognition and relation extraction as a multi-head selection problem , 2018, Expert Syst. Appl..

[10]  Claire Cardie,et al.  Investigating LSTMs for Joint Extraction of Opinion Entities and Relations , 2016, ACL.

[11]  Mari Ostendorf,et al.  Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction , 2018, EMNLP.

[12]  Jianfei Yu,et al.  Global Inference for Aspect and Opinion Terms Co-Extraction Based on Multi-Task Neural Networks , 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[13]  Yue Zhang,et al.  End-to-End Neural Relation Extraction with Global Optimization , 2017, EMNLP.

[14]  Xuanjing Huang,et al.  Phrase Dependency Parsing for Opinion Mining , 2009, EMNLP.

[15]  Heng Ji,et al.  Incremental Joint Extraction of Entity Mentions and Relations , 2014, ACL.

[16]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[17]  Philip S. Yu,et al.  BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis , 2019, NAACL.

[18]  Xin Li,et al.  Aspect Term Extraction with History Attention and Selective Transformation , 2018, IJCAI.

[19]  Rohit J. Kate,et al.  Joint Entity and Relation Extraction Using Card-Pyramid Parsing , 2010, CoNLL.

[20]  Kenton Lee,et al.  Learning Recurrent Span Representations for Extractive Question Answering , 2016, ArXiv.

[21]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

[22]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[23]  Zhen Wu,et al.  Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling , 2019, NAACL.

[24]  Makoto Miwa,et al.  End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures , 2016, ACL.

[25]  Luke S. Zettlemoyer,et al.  Higher-Order Coreference Resolution with Coarse-to-Fine Inference , 2018, NAACL.

[26]  Shafiq R. Joty,et al.  Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings , 2015, EMNLP.

[27]  Ming Zhou,et al.  Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction , 2016, IJCAI.

[28]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[29]  Sinno Jialin Pan,et al.  Recursive Neural Structural Correspondence Network for Cross-domain Aspect and Opinion Co-Extraction , 2018, ACL.

[30]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[31]  Peng Zhou,et al.  Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme , 2017, ACL.

[32]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[33]  Luke S. Zettlemoyer,et al.  Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations , 2011, ACL.

[34]  Jun Zhao,et al.  Opinion Target Extraction Using Partially-Supervised Word Alignment Model , 2013, IJCAI.

[35]  Xiaokui Xiao,et al.  Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis , 2016, EMNLP.

[36]  Xin Li,et al.  Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction , 2017, EMNLP.