Dynamic Topic Tracker for KB-to-Text Generation

Zihao Fu, Lidong Bing, Wai Lam, Shoaib Jameel


Abstract
Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences. However, most of the existing models suffer from the off-topic problem, namely, the models are prone to generate some unrelated clauses that are somehow involved with certain input terms regardless of the given input data. This problem seriously degrades the quality of the generation results. In this paper, we propose a novel dynamic topic tracker for solving this problem. Different from existing models, our proposed model learns a global hidden representation for topics and recognizes the corresponding topic during each generation step. The recognized topic is used as additional information to guide the generation process and thus alleviates the off-topic problem. The experimental results show that our proposed model can enhance the performance of sentence generation and the off-topic problem is significantly mitigated.
Anthology ID:
2020.coling-main.215
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2369–2380
Language:
URL:
https://aclanthology.org/2020.coling-main.215
DOI:
10.18653/v1/2020.coling-main.215
Bibkey:
Cite (ACL):
Zihao Fu, Lidong Bing, Wai Lam, and Shoaib Jameel. 2020. Dynamic Topic Tracker for KB-to-Text Generation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2369–2380, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Dynamic Topic Tracker for KB-to-Text Generation (Fu et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.215.pdf
Data
DBpediaWebNLG