IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG

arXiv:2210.13829v3 Announce Type: replace
Abstract: Some Natural Language Generation (NLG) tasks require both faithfulness and diversity. The decoding strategy is intensively related to the quality of the generated text. Strategies such as beam search, greedy search, etc., perform with low diversity and high repetition. On the other hand, guided decoding, the solution towards diversity, may generate unfaithful expressions. To this end, this paper presents Information Filter upon Diversity-Improved Decoding (IFDID) to obtain the tradeoff between diversity and faithfulness. IFDID is …

abstract arxiv cs.cl decoding diversity etc filter generated information language language generation low natural natural language natural language generation nlg quality search strategies strategy tasks text type