Transferable end-to-end aspect-based sentiment analysis with selective adversarial learning

Li，Zheng1; Li，Xin2; Wei，Ying3; Bing，Lidong4; Zhang，Yu5; Yang，Qiang1

2020

EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference

4590-4600

Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve fine-grained (word-level) adaptation. Empirically, extensive experiments demonstrate the effectiveness of the proposed SAL method.

其他

英语

EI

20201908639116

Computational linguistics

Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory:721.1 ; Data Processing and Image Processing:723.2

2-s2.0-85084309273

Scopus

1.Hong Kong University of Science and Technology,Hong Kong
2.Chinese University of Hong Kong,Hong Kong
3.Tencent AI Lab,Shenzhen,China
4.R&D Center Singapore,Machine Intelligence Technology,Alibaba DAMO Academy,China
5.Southern University of Science and Technology,Shenzhen,China

Li，Zheng,Li，Xin,Wei，Ying,et al. Transferable end-to-end aspect-based sentiment analysis with selective adversarial learning[C],2020:4590-4600.