@inproceedings{marton-toutanova-2016-e,
title = "{E}-{TIPSY}: Search Query Corpus Annotated with Entities, Term Importance, {POS} Tags, and Syntactic Parses",
author = "Marton, Yuval and
Toutanova, Kristina",
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/L16-1106",
pages = "672--676",
abstract = "We present E-TIPSY, a search query corpus annotated with named Entities, Term Importance, POS tags, and SYntactic parses. This corpus contains crowdsourced (gold) annotations of the three most important terms in each query. In addition, it contains automatically produced annotations of named entities, part-of-speech tags, and syntactic parses for the same queries. This corpus comes in two formats: (1) Sober Subset: annotations that two or more crowd workers agreed upon, and (2) Full Glass: all annotations. We analyze the strikingly low correlation between term importance and syntactic headedness, which invites research into effective ways of combining these different signals. Our corpus can serve as a benchmark for term importance methods aimed at improving search engine quality and as an initial step toward developing a dataset of gold linguistic analysis of web search queries. In addition, it can be used as a basis for linguistic inquiries into the kind of expressions used in search.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marton-toutanova-2016-e">
<titleInfo>
<title>E-TIPSY: Search Query Corpus Annotated with Entities, Term Importance, POS Tags, and Syntactic Parses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Marton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</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>We present E-TIPSY, a search query corpus annotated with named Entities, Term Importance, POS tags, and SYntactic parses. This corpus contains crowdsourced (gold) annotations of the three most important terms in each query. In addition, it contains automatically produced annotations of named entities, part-of-speech tags, and syntactic parses for the same queries. This corpus comes in two formats: (1) Sober Subset: annotations that two or more crowd workers agreed upon, and (2) Full Glass: all annotations. We analyze the strikingly low correlation between term importance and syntactic headedness, which invites research into effective ways of combining these different signals. Our corpus can serve as a benchmark for term importance methods aimed at improving search engine quality and as an initial step toward developing a dataset of gold linguistic analysis of web search queries. In addition, it can be used as a basis for linguistic inquiries into the kind of expressions used in search.</abstract>
<identifier type="citekey">marton-toutanova-2016-e</identifier>
<location>
<url>https://aclanthology.org/L16-1106</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>672</start>
<end>676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T E-TIPSY: Search Query Corpus Annotated with Entities, Term Importance, POS Tags, and Syntactic Parses
%A Marton, Yuval
%A Toutanova, Kristina
%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 marton-toutanova-2016-e
%X We present E-TIPSY, a search query corpus annotated with named Entities, Term Importance, POS tags, and SYntactic parses. This corpus contains crowdsourced (gold) annotations of the three most important terms in each query. In addition, it contains automatically produced annotations of named entities, part-of-speech tags, and syntactic parses for the same queries. This corpus comes in two formats: (1) Sober Subset: annotations that two or more crowd workers agreed upon, and (2) Full Glass: all annotations. We analyze the strikingly low correlation between term importance and syntactic headedness, which invites research into effective ways of combining these different signals. Our corpus can serve as a benchmark for term importance methods aimed at improving search engine quality and as an initial step toward developing a dataset of gold linguistic analysis of web search queries. In addition, it can be used as a basis for linguistic inquiries into the kind of expressions used in search.
%U https://aclanthology.org/L16-1106
%P 672-676
Markdown (Informal)
[E-TIPSY: Search Query Corpus Annotated with Entities, Term Importance, POS Tags, and Syntactic Parses](https://aclanthology.org/L16-1106) (Marton & Toutanova, LREC 2016)
ACL