Abstract
Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline manner, with aspect term extraction performed first, followed by sentiment predictions toward the extracted aspect terms. While easier to develop, such an approach does not fully exploit joint information from the two subtasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment corpus. In this paper, we propose an interactive multi-task learning network (IMN) which is able to jointly learn multiple related tasks simultaneously at both the token level as well as the document level. Unlike conventional multi-task learning methods that rely on learning common features for the different tasks, IMN introduces a message passing architecture where information is iteratively passed to different tasks through a shared set of latent variables. Experimental results demonstrate superior performance of the proposed method against multiple baselines on three benchmark datasets.- Anthology ID:
- P19-1048
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 504–515
- Language:
- URL:
- https://aclanthology.org/P19-1048
- DOI:
- 10.18653/v1/P19-1048
- Cite (ACL):
- Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2019. An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 504–515, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis (He et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/P19-1048.pdf
- Code
- lixin4ever/E2E-TBSA + additional community code
- Data
- SemEval 2014 Task 4 Sub Task 2