Content Order-Controllable MR-to-Text
Content order is critical in natural language generation (NLG) for emphasizing the focus of a generated text passage. In this paper, we propose a novel MR (meaning representation)-to-text method that controls the order of the MR values in a generated text passage based on the given order constraints...
Main Authors: | Keisuke Toyama, Katsuhito Sudoh, Satoshi Nakamura |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10320352/ |
Similar Items
-
Survey of Deep Learning Table-to-Text Generation
by: HU Kang, XI Xuefeng, CUI Zhiming, ZHOU Yueyao, QIU Yajin
Published: (2022-11-01) -
Application of Generative Adversarial Networks and Shapley Algorithm Based on Easy Data Augmentation for Imbalanced Text Data
by: Jheng-Long Wu, et al.
Published: (2022-10-01) -
Data augmentation for Arabic text classification: a review of current methods, challenges and prospective directions
by: Samia F. Abdhood, et al.
Published: (2025-03-01) -
Text augmentation using a graph-based approach and clonal selection algorithm
by: Hadeer Ahmed, et al.
Published: (2023-03-01) -
Leveraging Synthetic Data for Improved Manipuri-English Code-Switched ASR
by: Naorem Karline Singh, et al.
Published: (2025-01-01)