Research Repository

Dynamic Topic Tracker for KB-to-Text Generation

Zihao, Fu and Bing, Lidong and Wai, Lam and Jameel, Mohammad Shoaib (2020) Dynamic Topic Tracker for KB-to-Text Generation. In: The 28th International Conference on Computational Linguistics (COLING), 2020-12-08 - 2020-12-13, Online. (In Press)

coling2020.pdf - Accepted Version

Download (379kB) | Preview


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 the 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.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: _not provided_
Uncontrolled Keywords: text generation, knowledge graphs, neural generation
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 23 Nov 2020 17:18
Last Modified: 13 Dec 2020 02:00

Actions (login required)

View Item View Item