@inproceedings{postma-etal-2016-addressing,
title = "Addressing the {MFS} Bias in {WSD} systems",
author = "Postma, Marten and
Izquierdo, Ruben and
Agirre, Eneko and
Rigau, German and
Vossen, Piek",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1268/",
pages = "1695--1700",
abstract = "Word Sense Disambiguation (WSD) systems tend to have a strong bias towards assigning the Most Frequent Sense (MFS), which results in high performance on the MFS but in a very low performance on the less frequent senses. We addressed the MFS bias in WSD systems by combining the output from a WSD system with a set of mostly static features to create a MFS classifier to decide when to and not to choose the MFS. The output from this MFS classifier, which is based on the Random Forest algorithm, is then used to modify the output from the original WSD system. We applied our classifier to one of the state-of-the-art supervised WSD systems, i.e. IMS, and to of the best state-of-the-art unsupervised WSD systems, i.e. UKB. Our main finding is that we are able to improve the system output in terms of choosing between the MFS and the less frequent senses. When we apply the MFS classifier to fine-grained WSD, we observe an improvement on the less frequent sense cases, whereas we maintain the overall recall."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="postma-etal-2016-addressing">
<titleInfo>
<title>Addressing the MFS Bias in WSD systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marten</namePart>
<namePart type="family">Postma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Sense Disambiguation (WSD) systems tend to have a strong bias towards assigning the Most Frequent Sense (MFS), which results in high performance on the MFS but in a very low performance on the less frequent senses. We addressed the MFS bias in WSD systems by combining the output from a WSD system with a set of mostly static features to create a MFS classifier to decide when to and not to choose the MFS. The output from this MFS classifier, which is based on the Random Forest algorithm, is then used to modify the output from the original WSD system. We applied our classifier to one of the state-of-the-art supervised WSD systems, i.e. IMS, and to of the best state-of-the-art unsupervised WSD systems, i.e. UKB. Our main finding is that we are able to improve the system output in terms of choosing between the MFS and the less frequent senses. When we apply the MFS classifier to fine-grained WSD, we observe an improvement on the less frequent sense cases, whereas we maintain the overall recall.</abstract>
<identifier type="citekey">postma-etal-2016-addressing</identifier>
<location>
<url>https://aclanthology.org/L16-1268/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1695</start>
<end>1700</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Addressing the MFS Bias in WSD systems
%A Postma, Marten
%A Izquierdo, Ruben
%A Agirre, Eneko
%A Rigau, German
%A Vossen, Piek
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F postma-etal-2016-addressing
%X Word Sense Disambiguation (WSD) systems tend to have a strong bias towards assigning the Most Frequent Sense (MFS), which results in high performance on the MFS but in a very low performance on the less frequent senses. We addressed the MFS bias in WSD systems by combining the output from a WSD system with a set of mostly static features to create a MFS classifier to decide when to and not to choose the MFS. The output from this MFS classifier, which is based on the Random Forest algorithm, is then used to modify the output from the original WSD system. We applied our classifier to one of the state-of-the-art supervised WSD systems, i.e. IMS, and to of the best state-of-the-art unsupervised WSD systems, i.e. UKB. Our main finding is that we are able to improve the system output in terms of choosing between the MFS and the less frequent senses. When we apply the MFS classifier to fine-grained WSD, we observe an improvement on the less frequent sense cases, whereas we maintain the overall recall.
%U https://aclanthology.org/L16-1268/
%P 1695-1700
Markdown (Informal)
[Addressing the MFS Bias in WSD systems](https://aclanthology.org/L16-1268/) (Postma et al., LREC 2016)
ACL
- Marten Postma, Ruben Izquierdo, Eneko Agirre, German Rigau, and Piek Vossen. 2016. Addressing the MFS Bias in WSD systems. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1695–1700, Portorož, Slovenia. European Language Resources Association (ELRA).