Exploiting Coarse-to-Fine Task Transfer for Aspect-Level Sentiment Classification
Open Access
- 17 July 2019
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 4253-4260
Abstract
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT). However, due to the especially expensive and labor-intensive labeling, existing public corpora in AT-level are all relatively small. Meanwhile, most of the previous methods rely on complicated structures with given scarce data, which largely limits the efficacy of the neural models. In this paper, we exploit a new direction named coarse-to-fine task transfer, which aims to leverage knowledge learned from a rich-resource source domain of the coarse-grained AC task, which is more easily accessible, to improve the learning in a low-resource target domain of the fine-grained AT task. To resolve both the aspect granularity inconsistency and feature mismatch between domains, we propose a Multi-Granularity Alignment Network (MGAN). In MGAN, a novel Coarse2Fine attention guided by an auxiliary task can help the AC task modeling at the same finegrained level with the AT task. To alleviate the feature false alignment, a contrastive feature alignment method is adopted to align aspect-specific feature representations semantically. In addition, a large-scale multi-domain dataset for the AC task is provided. Empirically, extensive experiments demonstrate the effectiveness of the MGAN.Keywords
This publication has 15 references indexed in Scilit:
- DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language UnderstandingProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTMProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Unified Deep Supervised Domain Adaptation and Generalization2017
- Recurrent Attention Network on Memory for Aspect Sentiment Analysis2017
- Attention-based LSTM for Aspect-level Sentiment Classification2016
- Aspect Level Sentiment Classification with Deep Memory Network2016
- Hierarchical Attention Networks for Document Classification2016
- Cross-Domain Sentiment Classification Using a Sentiment Sensitive ThesaurusIEEE Transactions on Knowledge and Data Engineering, 2012
- Opinion Word Expansion and Target Extraction through Double PropagationComputational Linguistics, 2011
- Cross-domain sentiment classification via spectral feature alignment2010