Abstract
In this paper, we propose a multi-channel convolutional neural network-long short-term memory (CNN-LSTM) model that consists of two parts: multi-channel CNN and LSTM to analyze the sentiments of short English messages from Twitter. Un-like a conventional CNN, the proposed model applies a multi-channel strategy that uses several filters of different length to extract active local n-gram features in different scales. This information is then sequentially composed using LSTM. By combining both CNN and LSTM, we can consider both local information within tweets and long-distance dependency across tweets in the classification process. Officially released results show that our system outperforms the baseline algo-rithm.- Anthology ID:
- S17-2134
- Volume:
- Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 796–801
- Language:
- URL:
- https://aclanthology.org/S17-2134
- DOI:
- 10.18653/v1/S17-2134
- Cite (ACL):
- Haowei Zhang, Jin Wang, Jixian Zhang, and Xuejie Zhang. 2017. YNU-HPCC at SemEval 2017 Task 4: Using A Multi-Channel CNN-LSTM Model for Sentiment Classification. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 796–801, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- YNU-HPCC at SemEval 2017 Task 4: Using A Multi-Channel CNN-LSTM Model for Sentiment Classification (Zhang et al., SemEval 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/S17-2134.pdf