.png){kind=icon}
Return
Syntax-controlled paraphrases generation with VAE and multi-task learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2024.101705.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Paraphrase generation is an important method for augmenting text data, which has a crucial role in Natural Language Generation (NLG). However, existing methods lack the ability to capture the semantic representation of input sentences and the syntactic structure of exemplars, which can easily lead to problems such as redundant content, semantic inaccuracies, and poor diversity. To tackle these challenges, we propose a Syntax-Controlled Paraphrase Generator (SCPG), which utilizes attention networks and VAE-based hidden variables to model the semantics of input sentences and the syntax of exemplars. In addition, in order to achieve controllability of the target paraphrase structure, we propose a method for learning semantic and syntactic representations based on multi-task learning, and successfully integrate the two through a gating mechanism. Extensive experimental results show that SCPG achieves SOTA results in terms of both semantic consistency and syntactic controllability, and is able to make a better trade-off between preserving semantics and novelty of sentence structure.
Keywords:
Controlled Paraphrase generation
Variational Auto-Encoder
Semantic representation
Syntactic structure
Natural Language Generation
Journal
C
IF:
3.4
Papers:
1.5K
Citations:
2.6K
Organization
Cited Papers
Blue mussel (Mytilus spp.) cultivation in mesohaline eutrophied inner coastal waters: mitigation potential, threats and cost effectiveness.png)
PeerJ
OAAI
PeerJIF0
OAAIShareSaveShareSaveShareSaveShareSaveShareSaveApplication of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game DesignSENSORS
OAAI
SENSORSIF3.5
OAAIShareSave
View more