@inproceedings{masson-paroubek-2020-nlp,
title = "{NLP} Analytics in Finance with {D}o{R}e: A {F}rench 250{M} Tokens Corpus of Corporate Annual Reports",
author = "Masson, Corentin and
Paroubek, Patrick",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.275",
pages = "2261--2267",
abstract = "Recent advances in neural computing and word embeddings for semantic processing open many new applications areas which had been left unaddressed so far because of inadequate language understanding capacity. But this new kind of approaches rely even more on training data to be operational. Corpora for financial applications exists, but most of them concern stock market prediction and are in English. To address this need for the French language and regulation oriented applications which require a deeper understanding of the text content, we hereby present {``}DoRe{''}, a French and dialectal French Corpus for NLP analytics in Finance, Regulation and Investment. This corpus is composed of: (a) 1769 Annual Reports from 336 companies among the most capitalized companies in: France (Euronext Paris) {\&} Belgium (Euronext Brussels), covering a time frame from 2009 to 2019, and (b) related MetaData containing information for each company about its ISIN code, capitalization and sector. This corpus is designed to be as modular as possible in order to allow for maximum reuse in different tasks pertaining to Economics, Finance and Regulation. After presenting existing resources, we relate the construction of the DoRe corpus and the rationale behind our choices, concluding on the spectrum of possible uses of this new resource for NLP applications.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="masson-paroubek-2020-nlp">
<titleInfo>
<title>NLP Analytics in Finance with DoRe: A French 250M Tokens Corpus of Corporate Annual Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Corentin</namePart>
<namePart type="family">Masson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Paroubek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Recent advances in neural computing and word embeddings for semantic processing open many new applications areas which had been left unaddressed so far because of inadequate language understanding capacity. But this new kind of approaches rely even more on training data to be operational. Corpora for financial applications exists, but most of them concern stock market prediction and are in English. To address this need for the French language and regulation oriented applications which require a deeper understanding of the text content, we hereby present “DoRe”, a French and dialectal French Corpus for NLP analytics in Finance, Regulation and Investment. This corpus is composed of: (a) 1769 Annual Reports from 336 companies among the most capitalized companies in: France (Euronext Paris) & Belgium (Euronext Brussels), covering a time frame from 2009 to 2019, and (b) related MetaData containing information for each company about its ISIN code, capitalization and sector. This corpus is designed to be as modular as possible in order to allow for maximum reuse in different tasks pertaining to Economics, Finance and Regulation. After presenting existing resources, we relate the construction of the DoRe corpus and the rationale behind our choices, concluding on the spectrum of possible uses of this new resource for NLP applications.</abstract>
<identifier type="citekey">masson-paroubek-2020-nlp</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.275</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2261</start>
<end>2267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP Analytics in Finance with DoRe: A French 250M Tokens Corpus of Corporate Annual Reports
%A Masson, Corentin
%A Paroubek, Patrick
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F masson-paroubek-2020-nlp
%X Recent advances in neural computing and word embeddings for semantic processing open many new applications areas which had been left unaddressed so far because of inadequate language understanding capacity. But this new kind of approaches rely even more on training data to be operational. Corpora for financial applications exists, but most of them concern stock market prediction and are in English. To address this need for the French language and regulation oriented applications which require a deeper understanding of the text content, we hereby present “DoRe”, a French and dialectal French Corpus for NLP analytics in Finance, Regulation and Investment. This corpus is composed of: (a) 1769 Annual Reports from 336 companies among the most capitalized companies in: France (Euronext Paris) & Belgium (Euronext Brussels), covering a time frame from 2009 to 2019, and (b) related MetaData containing information for each company about its ISIN code, capitalization and sector. This corpus is designed to be as modular as possible in order to allow for maximum reuse in different tasks pertaining to Economics, Finance and Regulation. After presenting existing resources, we relate the construction of the DoRe corpus and the rationale behind our choices, concluding on the spectrum of possible uses of this new resource for NLP applications.
%U https://aclanthology.org/2020.lrec-1.275
%P 2261-2267
Markdown (Informal)
[NLP Analytics in Finance with DoRe: A French 250M Tokens Corpus of Corporate Annual Reports](https://aclanthology.org/2020.lrec-1.275) (Masson & Paroubek, LREC 2020)
ACL