Abstract
Emphasis Selection is a newly proposed task which focuses on choosing words for emphasis in short sentences. Traditional methods only consider the sequence information of a sentence while ignoring the rich sentence structure and word relationship information. In this paper, we propose a new framework that considers sentence structure via a sentence structure graph and word relationship via a word similarity graph. The sentence structure graph is derived from the parse tree of a sentence. The word similarity graph allows nodes to share information with their neighbors since we argue that in emphasis selection, similar words are more likely to be emphasized together. Graph neural networks are employed to learn the representation of each node of these two graphs. Experimental results demonstrate that our framework can achieve superior performance.- Anthology ID:
- 2021.ranlp-1.175
- Volume:
- Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
- Month:
- September
- Year:
- 2021
- Address:
- Held Online
- Editors:
- Ruslan Mitkov, Galia Angelova
- Venue:
- RANLP
- SIG:
- Publisher:
- INCOMA Ltd.
- Note:
- Pages:
- 1559–1566
- Language:
- URL:
- https://aclanthology.org/2021.ranlp-1.175
- DOI:
- Cite (ACL):
- Haoran Yang and Wai Lam. 2021. Sentence Structure and Word Relationship Modeling for Emphasis Selection. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1559–1566, Held Online. INCOMA Ltd..
- Cite (Informal):
- Sentence Structure and Word Relationship Modeling for Emphasis Selection (Yang & Lam, RANLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.ranlp-1.175.pdf
- Code
- lhryang/emphasis-selection