FAR-ASS: Fact-aware reinforced abstractive sentence summarization
作者：
Highlights：
• For natural language generation tasks, fact fabrication is a serious problem.
• An automatic fact extraction scheme leveraging open information extraction and dependency parser tools to extract the structured fact tuples.
• A factual correctness score function that takes into account the factual accuracy and the factual redundancy.
• A framework that improves the informativeness and the factual correctness by jointly optimize a mixed-objective learning function via reinforcement learning.
摘要
•For natural language generation tasks, fact fabrication is a serious problem.•An automatic fact extraction scheme leveraging open information extraction and dependency parser tools to extract the structured fact tuples.•A factual correctness score function that takes into account the factual accuracy and the factual redundancy.•A framework that improves the informativeness and the factual correctness by jointly optimize a mixed-objective learning function via reinforcement learning.
论文关键词：NLP,Abstractive summarization,Reinforcement learning,Sequence-to-sequence,Factual correctness
论文评审过程：Received 23 September 2020, Revised 30 November 2020, Accepted 18 December 2020, Available online 19 January 2021, Version of Record 19 January 2021.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102478
