Towards Informative Open-ended Text Generation with Dynamic Knowledge Triples
Submission Type: Regular Long Paper
Submission Track: Natural Language Generation
Keywords: Informativeness, Knowledge graph, open-ended text generation
Abstract: Pretrained language models (PLMs), especially large language models (LLMs) demonstrate impressive capabilities in open-ended text generation. While our statistical results show that LLMs often suffer from over-concentrated information, where the generated texts overly focus on the given prompt and fail to provide sufficient background and detailed information as humans do. To address this issue, we propose a dynamic knowledge-guided informative open-ended text generation approach, that utilizes a knowledge graph to help the model generate more contextually related entities and detailed facts. Specifically, we first employ a local knowledge filter to extract relevant knowledge from the comprehensive knowledge graph for a given topic sentence. Then we introduce a dynamic knowledge selector to predict the entity to be mentioned in the subsequent sentence. Finally, we utilize a knowledge-enhanced text generator to produce a more informative output. To evaluate the effectiveness of our approach, we evaluate the proposed approach in two scenarios: fine-tuning for small PLMs and prompt tuning for LLMs. Experimental results show that our approach could generate more informative texts than baselines.
Submission Number: 2716
Loading