@inproceedings{tezekbayev-etal-2022-speeding,
title = "Speeding Up Entmax",
author = "Tezekbayev, Maxat and
Nikoulina, Vassilina and
Gall{\'e}, Matthias and
Assylbekov, Zhenisbek",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.86",
doi = "10.18653/v1/2022.findings-naacl.86",
pages = "1142--1158",
abstract = "Softmax is the de facto standard for normalizing logits in modern neural networks for language processing. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being selected at each generation step, leading to a variety of reported problems in text generation. $\alpha$-entmax of Peters et al. (2019) solves this problem, but is unfortunately slower than softmax. In this paper, we propose an alternative to $\alpha$-entmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tezekbayev-etal-2022-speeding">
<titleInfo>
<title>Speeding Up Entmax</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxat</namePart>
<namePart type="family">Tezekbayev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilina</namePart>
<namePart type="family">Nikoulina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Gallé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenisbek</namePart>
<namePart type="family">Assylbekov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Softmax is the de facto standard for normalizing logits in modern neural networks for language processing. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being selected at each generation step, leading to a variety of reported problems in text generation. α-entmax of Peters et al. (2019) solves this problem, but is unfortunately slower than softmax. In this paper, we propose an alternative to α-entmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task.</abstract>
<identifier type="citekey">tezekbayev-etal-2022-speeding</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.86</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.86</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1142</start>
<end>1158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speeding Up Entmax
%A Tezekbayev, Maxat
%A Nikoulina, Vassilina
%A Gallé, Matthias
%A Assylbekov, Zhenisbek
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F tezekbayev-etal-2022-speeding
%X Softmax is the de facto standard for normalizing logits in modern neural networks for language processing. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being selected at each generation step, leading to a variety of reported problems in text generation. α-entmax of Peters et al. (2019) solves this problem, but is unfortunately slower than softmax. In this paper, we propose an alternative to α-entmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task.
%R 10.18653/v1/2022.findings-naacl.86
%U https://aclanthology.org/2022.findings-naacl.86
%U https://doi.org/10.18653/v1/2022.findings-naacl.86
%P 1142-1158
Markdown (Informal)
[Speeding Up Entmax](https://aclanthology.org/2022.findings-naacl.86) (Tezekbayev et al., Findings 2022)
ACL
- Maxat Tezekbayev, Vassilina Nikoulina, Matthias Gallé, and Zhenisbek Assylbekov. 2022. Speeding Up Entmax. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1142–1158, Seattle, United States. Association for Computational Linguistics.