@inproceedings{hedderich-klakow-2018-training,
title = "Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data",
author = "Hedderich, Michael A. and
Klakow, Dietrich",
editor = "Haffari, Reza and
Cherry, Colin and
Foster, George and
Khadivi, Shahram and
Salehi, Bahar",
booktitle = "Proceedings of the Workshop on Deep Learning Approaches for Low-Resource {NLP}",
month = jul,
year = "2018",
address = "Melbourne",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3402",
doi = "10.18653/v1/W18-3402",
pages = "12--18",
abstract = "Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier{'}s performance when trained on this data. We propose a noise layer that is added to a neural network architecture. This allows modeling the noise and train on a combination of clean and noisy data. We show that in a low-resource NER task we can improve performance by up to 35{\%} by using additional, noisy data and handling the noise.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hedderich-klakow-2018-training">
<titleInfo>
<title>Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Hedderich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bahar</namePart>
<namePart type="family">Salehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier’s performance when trained on this data. We propose a noise layer that is added to a neural network architecture. This allows modeling the noise and train on a combination of clean and noisy data. We show that in a low-resource NER task we can improve performance by up to 35% by using additional, noisy data and handling the noise.</abstract>
<identifier type="citekey">hedderich-klakow-2018-training</identifier>
<identifier type="doi">10.18653/v1/W18-3402</identifier>
<location>
<url>https://aclanthology.org/W18-3402</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>12</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data
%A Hedderich, Michael A.
%A Klakow, Dietrich
%Y Haffari, Reza
%Y Cherry, Colin
%Y Foster, George
%Y Khadivi, Shahram
%Y Salehi, Bahar
%S Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne
%F hedderich-klakow-2018-training
%X Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier’s performance when trained on this data. We propose a noise layer that is added to a neural network architecture. This allows modeling the noise and train on a combination of clean and noisy data. We show that in a low-resource NER task we can improve performance by up to 35% by using additional, noisy data and handling the noise.
%R 10.18653/v1/W18-3402
%U https://aclanthology.org/W18-3402
%U https://doi.org/10.18653/v1/W18-3402
%P 12-18
Markdown (Informal)
[Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data](https://aclanthology.org/W18-3402) (Hedderich & Klakow, ACL 2018)
ACL