@inproceedings{el-haj-etal-2014-detecting,
title = "Detecting Document Structure in a Very Large Corpus of {UK} Financial Reports",
author = "El-Haj, Mahmoud and
Rayson, Paul and
Young, Steve and
Walker, Martin",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/402_Paper.pdf",
pages = "1335--1338",
abstract = "In this paper we present the evaluation of our automatic methods for detecting and extracting document structure in annual financial reports. The work presented is part of the Corporate Financial Information Environment (CFIE) project in which we are using Natural Language Processing (NLP) techniques to study the causes and consequences of corporate disclosure and financial reporting outcomes. We aim to uncover the determinants of financial reporting quality and the factors that influence the quality of information disclosed to investors beyond the financial statements. The CFIE consists of the supply of information by firms to investors, and the mediating influences of information intermediaries on the timing, relevance and reliability of information available to investors. It is important to compare and contrast specific elements or sections of each annual financial report across our entire corpus rather than working at the full document level. We show that the values of some metrics e.g. readability will vary across sections, thus improving on previous research research based on full texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-haj-etal-2014-detecting">
<titleInfo>
<title>Detecting Document Structure in a Very Large Corpus of UK Financial Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present the evaluation of our automatic methods for detecting and extracting document structure in annual financial reports. The work presented is part of the Corporate Financial Information Environment (CFIE) project in which we are using Natural Language Processing (NLP) techniques to study the causes and consequences of corporate disclosure and financial reporting outcomes. We aim to uncover the determinants of financial reporting quality and the factors that influence the quality of information disclosed to investors beyond the financial statements. The CFIE consists of the supply of information by firms to investors, and the mediating influences of information intermediaries on the timing, relevance and reliability of information available to investors. It is important to compare and contrast specific elements or sections of each annual financial report across our entire corpus rather than working at the full document level. We show that the values of some metrics e.g. readability will vary across sections, thus improving on previous research research based on full texts.</abstract>
<identifier type="citekey">el-haj-etal-2014-detecting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/402_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1335</start>
<end>1338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Document Structure in a Very Large Corpus of UK Financial Reports
%A El-Haj, Mahmoud
%A Rayson, Paul
%A Young, Steve
%A Walker, Martin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F el-haj-etal-2014-detecting
%X In this paper we present the evaluation of our automatic methods for detecting and extracting document structure in annual financial reports. The work presented is part of the Corporate Financial Information Environment (CFIE) project in which we are using Natural Language Processing (NLP) techniques to study the causes and consequences of corporate disclosure and financial reporting outcomes. We aim to uncover the determinants of financial reporting quality and the factors that influence the quality of information disclosed to investors beyond the financial statements. The CFIE consists of the supply of information by firms to investors, and the mediating influences of information intermediaries on the timing, relevance and reliability of information available to investors. It is important to compare and contrast specific elements or sections of each annual financial report across our entire corpus rather than working at the full document level. We show that the values of some metrics e.g. readability will vary across sections, thus improving on previous research research based on full texts.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/402_Paper.pdf
%P 1335-1338
Markdown (Informal)
[Detecting Document Structure in a Very Large Corpus of UK Financial Reports](http://www.lrec-conf.org/proceedings/lrec2014/pdf/402_Paper.pdf) (El-Haj et al., LREC 2014)
ACL