Screening through a broad pool: Towards better diversity for lexically constrained text generation
Lexically constrained text generation (CTG) is to generate text that contains given constrained keywords. However, the text diversity of existing models is still unsatisfactory. In this paper, we propose a lightweight dynamic refinement strategy that aims at increasing the randomness of inference to...
Saved in:
Main Authors: | YUAN, Changsen, HUANG, Heyan, CAO, Yixin, CAO, Qianwen |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8478 https://ink.library.smu.edu.sg/context/sis_research/article/9481/viewcontent/ScreeningBroadPool_av.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Evaluating keyword selection methods for WEBSOM text archives
by: Azcarraga, A.P., et al.
Published: (2013) -
Extraction of Text from Images and Videos
by: PHAN QUY TRUNG
Published: (2014) -
Recognition of video text through temporal integration
by: Phan, T.Q., et al.
Published: (2014) -
Text localization in web images using probabilistic candidate selection model
by: Situ, L., et al.
Published: (2013) -
Prompt tuning on Graph-Augmented Low-Resource text classification
by: WEN, Zhihao, et al.
Published: (2024)