@inproceedings{ilievski-etal-2016-semantic,
title = "Semantic overfitting: what {`}world{'} do we consider when evaluating disambiguation of text?",
author = "Ilievski, Filip and
Postma, Marten and
Vossen, Piek",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1112",
pages = "1180--1191",
abstract = "Semantic text processing faces the challenge of defining the relation between lexical expressions and the world to which they make reference within a period of time. It is unclear whether the current test sets used to evaluate disambiguation tasks are representative for the full complexity considering this time-anchored relation, resulting in semantic overfitting to a specific period and the frequent phenomena within. We conceptualize and formalize a set of metrics which evaluate this complexity of datasets. We provide evidence for their applicability on five different disambiguation tasks. To challenge semantic overfitting of disambiguation systems, we propose a time-based, metric-aware method for developing datasets in a systematic and semi-automated manner, as well as an event-based QA task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ilievski-etal-2016-semantic">
<titleInfo>
<title>Semantic overfitting: what ‘world’ do we consider when evaluating disambiguation of text?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Ilievski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Semantic text processing faces the challenge of defining the relation between lexical expressions and the world to which they make reference within a period of time. It is unclear whether the current test sets used to evaluate disambiguation tasks are representative for the full complexity considering this time-anchored relation, resulting in semantic overfitting to a specific period and the frequent phenomena within. We conceptualize and formalize a set of metrics which evaluate this complexity of datasets. We provide evidence for their applicability on five different disambiguation tasks. To challenge semantic overfitting of disambiguation systems, we propose a time-based, metric-aware method for developing datasets in a systematic and semi-automated manner, as well as an event-based QA task.</abstract>
<identifier type="citekey">ilievski-etal-2016-semantic</identifier>
<location>
<url>https://aclanthology.org/C16-1112</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>1180</start>
<end>1191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic overfitting: what ‘world’ do we consider when evaluating disambiguation of text?
%A Ilievski, Filip
%A Postma, Marten
%A Vossen, Piek
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F ilievski-etal-2016-semantic
%X Semantic text processing faces the challenge of defining the relation between lexical expressions and the world to which they make reference within a period of time. It is unclear whether the current test sets used to evaluate disambiguation tasks are representative for the full complexity considering this time-anchored relation, resulting in semantic overfitting to a specific period and the frequent phenomena within. We conceptualize and formalize a set of metrics which evaluate this complexity of datasets. We provide evidence for their applicability on five different disambiguation tasks. To challenge semantic overfitting of disambiguation systems, we propose a time-based, metric-aware method for developing datasets in a systematic and semi-automated manner, as well as an event-based QA task.
%U https://aclanthology.org/C16-1112
%P 1180-1191
Markdown (Informal)
[Semantic overfitting: what ‘world’ do we consider when evaluating disambiguation of text?](https://aclanthology.org/C16-1112) (Ilievski et al., COLING 2016)
ACL