@inproceedings{lukasik-etal-2020-semantic,
title = "Semantic Label Smoothing for Sequence to Sequence Problems",
author = "Lukasik, Michal and
Jain, Himanshu and
Menon, Aditya and
Kim, Seungyeon and
Bhojanapalli, Srinadh and
Yu, Felix and
Kumar, Sanjiv",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.405/",
doi = "10.18653/v1/2020.emnlp-main.405",
pages = "4992--4998",
abstract = "Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such methods directly to seq2seq settings, such as Machine Translation, is challenging: the large target output space of such problems makes it intractable to apply label smoothing over all possible outputs. Most existing approaches for seq2seq settings either do token level smoothing, or smooth over sequences generated by randomly substituting tokens in the target sequence. Unlike these works, in this paper, we propose a technique that smooths over \textit{well formed} relevant sequences that not only have sufficient n-gram overlap with the target sequence, but are also \textit{semantically similar}. Our method shows a consistent and significant improvement over the state-of-the-art techniques on different datasets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lukasik-etal-2020-semantic">
<titleInfo>
<title>Semantic Label Smoothing for Sequence to Sequence Problems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Lukasik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Himanshu</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Menon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungyeon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinadh</namePart>
<namePart type="family">Bhojanapalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjiv</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such methods directly to seq2seq settings, such as Machine Translation, is challenging: the large target output space of such problems makes it intractable to apply label smoothing over all possible outputs. Most existing approaches for seq2seq settings either do token level smoothing, or smooth over sequences generated by randomly substituting tokens in the target sequence. Unlike these works, in this paper, we propose a technique that smooths over well formed relevant sequences that not only have sufficient n-gram overlap with the target sequence, but are also semantically similar. Our method shows a consistent and significant improvement over the state-of-the-art techniques on different datasets.</abstract>
<identifier type="citekey">lukasik-etal-2020-semantic</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.405</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.405/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4992</start>
<end>4998</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Label Smoothing for Sequence to Sequence Problems
%A Lukasik, Michal
%A Jain, Himanshu
%A Menon, Aditya
%A Kim, Seungyeon
%A Bhojanapalli, Srinadh
%A Yu, Felix
%A Kumar, Sanjiv
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lukasik-etal-2020-semantic
%X Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such methods directly to seq2seq settings, such as Machine Translation, is challenging: the large target output space of such problems makes it intractable to apply label smoothing over all possible outputs. Most existing approaches for seq2seq settings either do token level smoothing, or smooth over sequences generated by randomly substituting tokens in the target sequence. Unlike these works, in this paper, we propose a technique that smooths over well formed relevant sequences that not only have sufficient n-gram overlap with the target sequence, but are also semantically similar. Our method shows a consistent and significant improvement over the state-of-the-art techniques on different datasets.
%R 10.18653/v1/2020.emnlp-main.405
%U https://aclanthology.org/2020.emnlp-main.405/
%U https://doi.org/10.18653/v1/2020.emnlp-main.405
%P 4992-4998
Markdown (Informal)
[Semantic Label Smoothing for Sequence to Sequence Problems](https://aclanthology.org/2020.emnlp-main.405/) (Lukasik et al., EMNLP 2020)
ACL
- Michal Lukasik, Himanshu Jain, Aditya Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix Yu, and Sanjiv Kumar. 2020. Semantic Label Smoothing for Sequence to Sequence Problems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4992–4998, Online. Association for Computational Linguistics.