@inproceedings{yang-etal-2024-frustratingly-simple,
title = "A Frustratingly Simple Decoding Method for Neural Text Generation",
author = "Yang, Haoran and
Cai, Deng and
Li, Huayang and
Bi, Wei and
Lam, Wai and
Shi, Shuming",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.47",
pages = "536--557",
abstract = "We introduce a frustratingly simple, highly efficient, and surprisingly effective decoding method, termed Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: We construct an anti-language model (anti-LM) based on previously generated text, which is employed to penalize the future generation of repetitive content. The anti-LM can be implemented as simple as an n-gram language model or a vectorized variant. In this way, FSD incurs no additional model parameters and negligible computational overhead (FSD can be as fast as greedy search). Despite its simplicity, FSD is surprisingly effective and generalizes across different datasets, models, and languages. Extensive experiments show that FSD outperforms established strong baselines in terms of generation quality, decoding speed, and universality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-frustratingly-simple">
<titleInfo>
<title>A Frustratingly Simple Decoding Method for Neural Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deng</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huayang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wai</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a frustratingly simple, highly efficient, and surprisingly effective decoding method, termed Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: We construct an anti-language model (anti-LM) based on previously generated text, which is employed to penalize the future generation of repetitive content. The anti-LM can be implemented as simple as an n-gram language model or a vectorized variant. In this way, FSD incurs no additional model parameters and negligible computational overhead (FSD can be as fast as greedy search). Despite its simplicity, FSD is surprisingly effective and generalizes across different datasets, models, and languages. Extensive experiments show that FSD outperforms established strong baselines in terms of generation quality, decoding speed, and universality.</abstract>
<identifier type="citekey">yang-etal-2024-frustratingly-simple</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.47</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>536</start>
<end>557</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Frustratingly Simple Decoding Method for Neural Text Generation
%A Yang, Haoran
%A Cai, Deng
%A Li, Huayang
%A Bi, Wei
%A Lam, Wai
%A Shi, Shuming
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yang-etal-2024-frustratingly-simple
%X We introduce a frustratingly simple, highly efficient, and surprisingly effective decoding method, termed Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: We construct an anti-language model (anti-LM) based on previously generated text, which is employed to penalize the future generation of repetitive content. The anti-LM can be implemented as simple as an n-gram language model or a vectorized variant. In this way, FSD incurs no additional model parameters and negligible computational overhead (FSD can be as fast as greedy search). Despite its simplicity, FSD is surprisingly effective and generalizes across different datasets, models, and languages. Extensive experiments show that FSD outperforms established strong baselines in terms of generation quality, decoding speed, and universality.
%U https://aclanthology.org/2024.lrec-main.47
%P 536-557
Markdown (Informal)
[A Frustratingly Simple Decoding Method for Neural Text Generation](https://aclanthology.org/2024.lrec-main.47) (Yang et al., LREC-COLING 2024)
ACL
- Haoran Yang, Deng Cai, Huayang Li, Wei Bi, Wai Lam, and Shuming Shi. 2024. A Frustratingly Simple Decoding Method for Neural Text Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 536–557, Torino, Italia. ELRA and ICCL.