[2L1-GS-2] Machine learning: NLP

[2L1-GS-2-04] Detection and fix of factual inconsistency contained in neural generated sentences

〇Keita Moriwaki¹, Shun Oono¹, Hiroaki Sugiyama², Masaki Shuzo¹, Eisaku Maeda¹ (1. Tokyo Denki University, 2. NTT Communication Science Laboratories)

Keywords:BERT, factual inconsistency problem, Dialogue

To constrain the factual inconsistency in neural generated sentences, we tried to postfix the inconsistent sentences.
Detection/modification models were trained by pseudo dataset which were rewritten from original dataset for the
neural sentence generator. Our experimental results show sequential process of detection and modification of
inconsistence was effective while single process of modification tended to change some consistent sentences. For
some remaining inconsistent sentences, other training datasets for detection and modification models to work
complementarily will improve the postfix performance.