Abstract
Deep convolutional neural networks excel at sentiment polarity classification, but tend to require substantial amounts of training data, which moreover differs quite significantly between domains. In this work, we present an approach to feed generic cues into the training process of such networks, leading to better generalization abilities given limited training data. We propose to induce sentiment embeddings via supervision on extrinsic data, which are then fed into the model via a dedicated memory-based component. We observe significant gains in effectiveness on a range of different datasets in seven different languages.- Anthology ID:
- P18-1235
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2524–2534
- Language:
- URL:
- https://aclanthology.org/P18-1235
- DOI:
- 10.18653/v1/P18-1235
- Cite (ACL):
- Xin Dong and Gerard de Melo. 2018. A Helping Hand: Transfer Learning for Deep Sentiment Analysis. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2524–2534, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- A Helping Hand: Transfer Learning for Deep Sentiment Analysis (Dong & de Melo, ACL 2018)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/P18-1235.pdf
- Data
- Multi-Domain Sentiment, SST, SST-2