Abstract
The coarse-to-fine (coarse2fine) methods have recently been widely used in the generation tasks. The methods first generate a rough sketch in the coarse stage and then use the sketch to get the final result in the fine stage. However, they usually lack the correction ability when getting a wrong sketch. To solve this problem, in this paper, we propose an improved coarse2fine model with a control mechanism, with which our method can control the influence of the sketch on the final results in the fine stage. Even if the sketch is wrong, our model still has the opportunity to get a correct result. We have experimented our model on the tasks of semantic parsing and math word problem solving. The results have shown the effectiveness of our proposed model.- Anthology ID:
- U19-1024
- Volume:
- Proceedings of the The 17th Annual Workshop of the Australasian Language Technology Association
- Month:
- 4--6 December
- Year:
- 2019
- Address:
- Sydney, Australia
- Venue:
- ALTA
- SIG:
- Publisher:
- Australasian Language Technology Association
- Note:
- Pages:
- 178–185
- Language:
- URL:
- https://aclanthology.org/U19-1024
- DOI:
- Cite (ACL):
- Wenyv Guan, Qianying Liu, Guangzhi Han, Bin Wang, and Sujian Li. 2019. An Improved Coarse-to-Fine Method for Solving Generation Tasks. In Proceedings of the The 17th Annual Workshop of the Australasian Language Technology Association, pages 178–185, Sydney, Australia. Australasian Language Technology Association.
- Cite (Informal):
- An Improved Coarse-to-Fine Method for Solving Generation Tasks (Guan et al., ALTA 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/U19-1024.pdf