MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies

26 May 2023

Papers citing "MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies"

7 / 7 papers shown

Title
A Measure-Theoretic Characterization of Tight Language Models Li Du Lucas Torroba Hennigen Tiago Pimentel Clara Meister Jason Eisner Ryan Cotterell 51 30 0 20 Dec 2022
Locally Typical Sampling Clara Meister Tiago Pimentel Gian Wiher Ryan Cotterell 165 88 0 01 Feb 2022
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation Bryan Eikema Wilker Aziz 32 132 0 20 May 2020
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training Margaret Li Stephen Roller Ilia Kulikov Sean Welleck Y-Lan Boureau Kyunghyun Cho Jason Weston 49 181 0 10 Nov 2019
On NMT Search Errors and Model Errors: Cat Got Your Tongue? Felix Stahlberg Bill Byrne LRM 41 152 0 27 Aug 2019
Unifying Human and Statistical Evaluation for Natural Language Generation Tatsunori B. Hashimoto Hugh Zhang Percy Liang 42 223 0 04 Apr 2019
Neural Machine Translation by Jointly Learning to Align and Translate Dzmitry Bahdanau Kyunghyun Cho Yoshua Bengio AIMat 331 27,205 0 01 Sep 2014