Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2112.08914
Cited By
Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
16 December 2021
Ilia Kulikov
M. Eremeev
Kyunghyun Cho
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling"
5 / 5 papers shown
Title
Tailoring Language Generation Models under Total Variation Distance
Haozhe Ji
Pei Ke
Zhipeng Hu
Rongsheng Zhang
Minlie Huang
28
18
0
26 Feb 2023
Reward Gaming in Conditional Text Generation
Richard Yuanzhe Pang
Vishakh Padmakumar
Thibault Sellam
Ankur P. Parikh
He He
29
24
0
16 Nov 2022
A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition
Darcey Riley
David Chiang
23
5
0
19 Oct 2022
The Implicit Length Bias of Label Smoothing on Beam Search Decoding
Bowen Liang
Pidong Wang
Yuan Cao
16
1
0
02 May 2022
Six Challenges for Neural Machine Translation
Philipp Koehn
Rebecca Knowles
AAML
AIMat
218
1,208
0
12 Jun 2017
1