Web: http://arxiv.org/abs/2209.10922

Sept. 23, 2022, 1:15 a.m. | Seonil Son, Jaeseo Lim, Youwon Jang, Jaeyoung Lee, Byoung-Tak Zhang

cs.CL updates on arXiv.org arxiv.org

Coherence is one of the critical factors that determine the quality of
writing. We propose writing relevance (WR) training method for neural
encoder-decoder natural language generation (NLG) models which improves
coherence of the continuation by leveraging negative examples. WR loss
regresses the vector representation of the context and generated sentence
toward positive continuation by contrasting it with the negatives. We compare
our approach with Unlikelihood (UL) training in a text continuation task on
commonsense natural language inference (NLI) corpora to …

arxiv examples negative

More from arxiv.org / cs.CL updates on arXiv.org

Research Scientists

@ ODU Research Foundation | Norfolk, Virginia

Embedded Systems Engineer (Robotics)

@ Neo Cybernetica | Bedford, New Hampshire

2023 Luis J. Alvarez and Admiral Grace M. Hopper Postdoc Fellowship in Computing Sciences

@ Lawrence Berkeley National Lab | San Francisco, CA

Senior Manager Data Scientist

@ NAV | Remote, US

Senior AI Research Scientist

@ Earth Species Project | Remote anywhere

Research Fellow- Center for Security and Emerging Technology (Multiple Opportunities)

@ University of California Davis | Washington, DC

Staff Fellow - Data Scientist

@ U.S. FDA/Center for Devices and Radiological Health | Silver Spring, Maryland

Staff Fellow - Senior Data Engineer

@ U.S. FDA/Center for Devices and Radiological Health | Silver Spring, Maryland

Machine Learning Data Engineer Intern (Jyoti Dharna)

@ Benson Hill | St. Louis, Missouri

Software Engineer / SDE I, Chime SDK Video Research Engineering

@ Amazon.com | East Palo Alto, California, USA

IND (New) Senior ML Ops Engineer - WiQ

@ Quantium | Hyderabad

Data Engineer

@ LendingTree | Remote