all AI news
Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG. (arXiv:2210.13829v1 [cs.CL])
Oct. 26, 2022, 1:16 a.m. | Han Meng, Xiaosong He, Zexing Chen, Feng Zhou
cs.CL updates on arXiv.org arxiv.org
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 a two-stage
decoding strategy leveraging …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne