paper-with-me

Papers

A Frustratingly Simple Decoding Method for Neural Text Generation

2023-05-22 · Haoran Yang, Deng Cai, Huayang Li, Wei Bi, Wai Lam, Shuming Shi

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.

📄 PDF Abstract BibTeX arXiv:2305.12675

Code (1)

lhryang/fsd 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingText Generation

Similar Papers 제목 키워드 기반

Frustratingly Easy Model Ensemble for Abstractive Summarization

2018-10-01 · EMNLP 2018 10 · Hayato Kobayashi

Ensemble methods, which combine multiple models at decoding time, are now widely known to be effective for text-generation tasks. However, they generally increase computational costs, and thus, there have been many studi…

Abstractive Text SummarizationDensity EstimationHeadline Generationmodel+3

Frustratingly Simple Few-Shot Slot Tagging

2021-08-01 · Findings (ACL) 2021 8 · Jianqiang Ma, Zeyu Yan, Chang Li, Yang Zhang

Frustratingly Simple Prompting-based Text Denoising

2024-02-24 · Jungyeul Park, Mengyang Qiu

This paper introduces a novel perspective on the automated essay scoring (AES) task, challenging the conventional view of the ASAP dataset as a static entity. Employing simple text denoising techniques using prompting, w…

Automated Essay ScoringDenoisingregression

A Frustratingly Simple Approach for End-to-End Image Captioning

2022-01-30 · Ziyang Luo, Yadong Xi, Rongsheng Zhang, Jing Ma

Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works …

DecoderImage CaptioningObjectText Generation

Frustratingly Easy Uncertainty Estimation for Distribution Shift

2021-06-07 · Tiago Salvador, Vikram Voleti, Alexander Iannantuono, Adam Oberman

Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domain adaptation. While the primary goal is …

Domain Adaptationimage-classificationImage ClassificationUnsupervised Domain Adaptation