A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training

3 May 2023

Papers citing "A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training"

5 / 5 papers shown

Title
The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model Kaito Takanami Takashi Takahashi Ayaka Sakata 29 0 0 27 Jan 2025
BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM Zhewen Shen Aditya Joshi Ruey-Cheng Chen CLL 31 2 0 17 Jun 2024
Relating Neural Text Degeneration to Exposure Bias Ting-Rui Chiang Yun-Nung Chen 37 16 0 17 Sep 2021
Fixing exposure bias with imitation learning needs powerful oracles L. Hormann Artem Sokolov 21 3 0 09 Sep 2021
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics Sebastian Gehrmann Tosin P. Adewumi Karmanya Aggarwal Pawan Sasanka Ammanamanchi Aremu Anuoluwapo ... Nishant Subramani Wei-ping Xu Diyi Yang Akhila Yerukola Jiawei Zhou VLM 238 254 0 02 Feb 2021