Abstract
Discourse Parsing and Sentiment Analysis are two fundamental tasks in Natural Language Processing that have been shown to be mutually beneficial. In this work, we design and compare two Neural Based models for jointly learning both tasks. In the proposed approach, we first create a vector representation for all the text segments in the input sentence. Next, we apply three different Recursive Neural Net models: one for discourse structure prediction, one for discourse relation prediction and one for sentiment analysis. Finally, we combine these Neural Nets in two different joint models: Multi-tasking and Pre-training. Our results on two standard corpora indicate that both methods result in improvements in each task but Multi-tasking has a bigger impact than Pre-training. Specifically for Discourse Parsing, we see improvements in the prediction of the set of contrastive relations.- Anthology ID:
- W17-5535
- Volume:
- Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
- Month:
- August
- Year:
- 2017
- Address:
- Saarbrücken, Germany
- Editors:
- Kristiina Jokinen, Manfred Stede, David DeVault, Annie Louis
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 289–298
- Language:
- URL:
- https://aclanthology.org/W17-5535
- DOI:
- 10.18653/v1/W17-5535
- Cite (ACL):
- Bita Nejat, Giuseppe Carenini, and Raymond Ng. 2017. Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 289–298, Saarbrücken, Germany. Association for Computational Linguistics.
- Cite (Informal):
- Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis (Nejat et al., SIGDIAL 2017)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/W17-5535.pdf
- Data
- SST, SST-2, SST-5