English

A Frustratingly Simple Decoding Method for Neural Text Generation

Computation and Language 2024-02-28 v2

Abstract

We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: we build an anti-LM based on previously generated text and use this anti-LM to penalize future generation of what has been generated. The anti-LM can be implemented as simple as an n-gram language model or a vectorized variant. In this way, FSD introduces no extra model parameters and negligible computational overhead (FSD can be as fast as greedy search). Despite the simplicity, FSD is surprisingly effective; Experiments show that FSD can outperform the canonical methods to date (i.e., nucleus sampling) as well as several strong baselines that were proposed recently.

Keywords

Cite

@article{arxiv.2305.12675,
  title  = {A Frustratingly Simple Decoding Method for Neural Text Generation},
  author = {Haoran Yang and Deng Cai and Huayang Li and Wei Bi and Wai Lam and Shuming Shi},
  journal= {arXiv preprint arXiv:2305.12675},
  year   = {2024}
}

Comments

LREC-Coling 2024

R2 v1 2026-06-28T10:40:50.930Z