CLMay 22, 2023

A Frustratingly Simple Decoding Method for Neural Text Generation

arXiv:2305.12675v288 citations
Originality Incremental advance
AI Analysis

This incremental improvement addresses efficiency and quality issues in text generation for NLP applications.

The paper tackles the problem of improving neural text generation by introducing a simple decoding method that penalizes repetition, achieving performance superior to nucleus sampling and recent baselines with negligible computational overhead.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes