Abstract
We propose a novel LSTM-based deep multi-task learning framework for aspect term extraction from user review sentences. Two LSTMs equipped with extended memories and neural memory operations are designed for jointly handling the extraction tasks of aspects and opinions via memory interactions. Sentimental sentence constraint is also added for more accurate prediction via another LSTM. Experiment results over two benchmark datasets demonstrate the effectiveness of our framework.- Anthology ID:
- D17-1310
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2886–2892
- Language:
- URL:
- https://aclanthology.org/D17-1310
- DOI:
- 10.18653/v1/D17-1310
- Cite (ACL):
- Xin Li and Wai Lam. 2017. Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2886–2892, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction (Li & Lam, EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/D17-1310.pdf