@inproceedings{dekker-van-der-goot-2020-synthetic,
title = "Synthetic Data for {E}nglish Lexical Normalization: How Close Can We Get to Manually Annotated Data?",
author = "Dekker, Kelly and
van der Goot, Rob",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.773",
pages = "6300--6309",
abstract = "Social media is a valuable data resource for various natural language processing (NLP) tasks. However, standard NLP tools were often designed with standard texts in mind, and their performance decreases heavily when applied to social media data. One solution to this problem is to adapt the input text to a more standard form, a task also referred to as normalization. Automatic approaches to normalization have shown that they can be used to improve performance on a variety of NLP tasks. However, all of these systems are supervised, thereby being heavily dependent on the availability of training data for the correct language and domain. In this work, we attempt to overcome this dependence by automatically generating training data for lexical normalization. Starting with raw tweets, we attempt two directions, to insert non-standardness (noise) and to automatically normalize in an unsupervised setting. Our best results are achieved by automatically inserting noise. We evaluate our approaches by using an existing lexical normalization system; our best scores are achieved by custom error generation system, which makes use of some manually created datasets. With this system, we score 94.29 accuracy on the test data, compared to 95.22 when it is trained on human-annotated data. Our best system which does not depend on any type of annotation is based on word embeddings and scores 92.04 accuracy. Finally, we perform an experiment in which we asked humans to predict whether a sentence was written by a human or generated by our best model. This experiment showed that in most cases it is hard for a human to detect automatically generated sentences.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dekker-van-der-goot-2020-synthetic">
<titleInfo>
<title>Synthetic Data for English Lexical Normalization: How Close Can We Get to Manually Annotated Data?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Dekker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Social media is a valuable data resource for various natural language processing (NLP) tasks. However, standard NLP tools were often designed with standard texts in mind, and their performance decreases heavily when applied to social media data. One solution to this problem is to adapt the input text to a more standard form, a task also referred to as normalization. Automatic approaches to normalization have shown that they can be used to improve performance on a variety of NLP tasks. However, all of these systems are supervised, thereby being heavily dependent on the availability of training data for the correct language and domain. In this work, we attempt to overcome this dependence by automatically generating training data for lexical normalization. Starting with raw tweets, we attempt two directions, to insert non-standardness (noise) and to automatically normalize in an unsupervised setting. Our best results are achieved by automatically inserting noise. We evaluate our approaches by using an existing lexical normalization system; our best scores are achieved by custom error generation system, which makes use of some manually created datasets. With this system, we score 94.29 accuracy on the test data, compared to 95.22 when it is trained on human-annotated data. Our best system which does not depend on any type of annotation is based on word embeddings and scores 92.04 accuracy. Finally, we perform an experiment in which we asked humans to predict whether a sentence was written by a human or generated by our best model. This experiment showed that in most cases it is hard for a human to detect automatically generated sentences.</abstract>
<identifier type="citekey">dekker-van-der-goot-2020-synthetic</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.773</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6300</start>
<end>6309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Data for English Lexical Normalization: How Close Can We Get to Manually Annotated Data?
%A Dekker, Kelly
%A van der Goot, Rob
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F dekker-van-der-goot-2020-synthetic
%X Social media is a valuable data resource for various natural language processing (NLP) tasks. However, standard NLP tools were often designed with standard texts in mind, and their performance decreases heavily when applied to social media data. One solution to this problem is to adapt the input text to a more standard form, a task also referred to as normalization. Automatic approaches to normalization have shown that they can be used to improve performance on a variety of NLP tasks. However, all of these systems are supervised, thereby being heavily dependent on the availability of training data for the correct language and domain. In this work, we attempt to overcome this dependence by automatically generating training data for lexical normalization. Starting with raw tweets, we attempt two directions, to insert non-standardness (noise) and to automatically normalize in an unsupervised setting. Our best results are achieved by automatically inserting noise. We evaluate our approaches by using an existing lexical normalization system; our best scores are achieved by custom error generation system, which makes use of some manually created datasets. With this system, we score 94.29 accuracy on the test data, compared to 95.22 when it is trained on human-annotated data. Our best system which does not depend on any type of annotation is based on word embeddings and scores 92.04 accuracy. Finally, we perform an experiment in which we asked humans to predict whether a sentence was written by a human or generated by our best model. This experiment showed that in most cases it is hard for a human to detect automatically generated sentences.
%U https://aclanthology.org/2020.lrec-1.773
%P 6300-6309
Markdown (Informal)
[Synthetic Data for English Lexical Normalization: How Close Can We Get to Manually Annotated Data?](https://aclanthology.org/2020.lrec-1.773) (Dekker & van der Goot, LREC 2020)
ACL