@inproceedings{nicolai-silfverberg-2020-noise,
title = "Noise Isn{'}t Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models",
author = "Nicolai, Garrett and
Silfverberg, Miikka",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.255",
doi = "10.18653/v1/2020.coling-main.255",
pages = "2837--2846",
abstract = "Morphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lower-data settings. We investigate one aspect of neural seq2seq models that we hypothesize contributes to overfitting - teacher forcing. By creating different training and test conditions, exposure bias increases the likelihood that a system too closely models its training data. Experiments show that teacher-forced models struggle to recover when they enter unknown territory. However, a simple modification to the training algorithm to more closely mimic test conditions creates models that are better able to generalize to unseen environments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nicolai-silfverberg-2020-noise">
<titleInfo>
<title>Noise Isn’t Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miikka</namePart>
<namePart type="family">Silfverberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Morphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lower-data settings. We investigate one aspect of neural seq2seq models that we hypothesize contributes to overfitting - teacher forcing. By creating different training and test conditions, exposure bias increases the likelihood that a system too closely models its training data. Experiments show that teacher-forced models struggle to recover when they enter unknown territory. However, a simple modification to the training algorithm to more closely mimic test conditions creates models that are better able to generalize to unseen environments.</abstract>
<identifier type="citekey">nicolai-silfverberg-2020-noise</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.255</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.255</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2837</start>
<end>2846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noise Isn’t Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models
%A Nicolai, Garrett
%A Silfverberg, Miikka
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F nicolai-silfverberg-2020-noise
%X Morphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lower-data settings. We investigate one aspect of neural seq2seq models that we hypothesize contributes to overfitting - teacher forcing. By creating different training and test conditions, exposure bias increases the likelihood that a system too closely models its training data. Experiments show that teacher-forced models struggle to recover when they enter unknown territory. However, a simple modification to the training algorithm to more closely mimic test conditions creates models that are better able to generalize to unseen environments.
%R 10.18653/v1/2020.coling-main.255
%U https://aclanthology.org/2020.coling-main.255
%U https://doi.org/10.18653/v1/2020.coling-main.255
%P 2837-2846
Markdown (Informal)
[Noise Isn’t Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models](https://aclanthology.org/2020.coling-main.255) (Nicolai & Silfverberg, COLING 2020)
ACL