@inproceedings{di-buono-2016-semi,
title = "Semi-automatic Parsing for Web Knowledge Extraction through Semantic Annotation",
author = "di Buono, Maria Pia",
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/L16-1113",
pages = "714--717",
abstract = "Parsing Web information, namely parsing content to find relevant documents on the basis of a user{'}s query, represents a crucial step to guarantee fast and accurate Information Retrieval (IR). Generally, an automated approach to such task is considered faster and cheaper than manual systems. Nevertheless, results do not seem have a high level of accuracy, indeed, as also Hjorland (2007) states, using stochastic algorithms entails: {\mbox{$\bullet$}} Low precision due to the indexing of common Atomic Linguistic Units (ALUs) or sentences. {\mbox{$\bullet$}} Low recall caused by the presence of synonyms. {\mbox{$\bullet$}} Generic results arising from the use of too broad or too narrow terms. Usually IR systems are based on invert text index, namely an index data structure storing a mapping from content to its locations in a database file, or in a document or a set of documents. In this paper we propose a system, by means of which we will develop a search engine able to process online documents, starting from a natural language query, and to return information to users. The proposed approach, based on the Lexicon-Grammar (LG) framework and its language formalization methodologies, aims at integrating a semantic annotation process for both query analysis and document retrieval.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-buono-2016-semi">
<titleInfo>
<title>Semi-automatic Parsing for Web Knowledge Extraction through Semantic Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</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>Parsing Web information, namely parsing content to find relevant documents on the basis of a user’s query, represents a crucial step to guarantee fast and accurate Information Retrieval (IR). Generally, an automated approach to such task is considered faster and cheaper than manual systems. Nevertheless, results do not seem have a high level of accuracy, indeed, as also Hjorland (2007) states, using stochastic algorithms entails: \bullet Low precision due to the indexing of common Atomic Linguistic Units (ALUs) or sentences. \bullet Low recall caused by the presence of synonyms. \bullet Generic results arising from the use of too broad or too narrow terms. Usually IR systems are based on invert text index, namely an index data structure storing a mapping from content to its locations in a database file, or in a document or a set of documents. In this paper we propose a system, by means of which we will develop a search engine able to process online documents, starting from a natural language query, and to return information to users. The proposed approach, based on the Lexicon-Grammar (LG) framework and its language formalization methodologies, aims at integrating a semantic annotation process for both query analysis and document retrieval.</abstract>
<identifier type="citekey">di-buono-2016-semi</identifier>
<location>
<url>https://aclanthology.org/L16-1113</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>714</start>
<end>717</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-automatic Parsing for Web Knowledge Extraction through Semantic Annotation
%A di Buono, Maria Pia
%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 di-buono-2016-semi
%X Parsing Web information, namely parsing content to find relevant documents on the basis of a user’s query, represents a crucial step to guarantee fast and accurate Information Retrieval (IR). Generally, an automated approach to such task is considered faster and cheaper than manual systems. Nevertheless, results do not seem have a high level of accuracy, indeed, as also Hjorland (2007) states, using stochastic algorithms entails: \bullet Low precision due to the indexing of common Atomic Linguistic Units (ALUs) or sentences. \bullet Low recall caused by the presence of synonyms. \bullet Generic results arising from the use of too broad or too narrow terms. Usually IR systems are based on invert text index, namely an index data structure storing a mapping from content to its locations in a database file, or in a document or a set of documents. In this paper we propose a system, by means of which we will develop a search engine able to process online documents, starting from a natural language query, and to return information to users. The proposed approach, based on the Lexicon-Grammar (LG) framework and its language formalization methodologies, aims at integrating a semantic annotation process for both query analysis and document retrieval.
%U https://aclanthology.org/L16-1113
%P 714-717
Markdown (Informal)
[Semi-automatic Parsing for Web Knowledge Extraction through Semantic Annotation](https://aclanthology.org/L16-1113) (di Buono, LREC 2016)
ACL