Multilingual financial narrative processing: analyzing annual reports in English, Spanish, and Portuguese

Mahmoud El-Haj; Paul Rayson; Paulo Alves; Carlos Herrero-Zorita; Steven Young

doi:10.1142/9789813274884_0013

Multilingual financial narrative processing: analyzing annual reports in English, Spanish, and Portuguese

Mahmoud El-Haj, Paul Rayson, Paulo Alves, Carlos Herrero-Zorita, Steven Young

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

14 Citations (Scopus)

Abstract

This chapter describes and evaluates the use of information extraction (IE) and natural language processing (NLP) methods for extraction and analysis of financial annual reports in three languages: English, Spanish, and Portuguese. The work described retains information on document structure which is needed to enable a clear distinction between narrative and financial statement components of annual reports and between individual sections within the narratives component. Extraction accuracy varies between languages with English exceeding 95%. We apply the extraction methods on a comprehensive sample of annual reports published by UK, Spanish, and Portuguese non-financial firms between 2003 and 2014.

Original language	English
Title of host publication	Multilingual text analysis
Subtitle of host publication	challenges, models, and approaches
Editors	Marina Litvak, Natalia Vanetik
Publisher	World Scientific Publishing Co.
Pages	441-463
Number of pages	23
ISBN (Electronic)	9789813274884
ISBN (Print)	9789813274877
DOIs	https://doi.org/10.1142/9789813274884_0013
Publication status	Published - 1 Jan 2019

Access to Document

10.1142/9789813274884_0013

Cite this

El-Haj, M., Rayson, P., Alves, P., Herrero-Zorita, C., & Young, S. (2019). Multilingual financial narrative processing: analyzing annual reports in English, Spanish, and Portuguese. In M. Litvak, & N. Vanetik (Eds.), Multilingual text analysis: challenges, models, and approaches (pp. 441-463). World Scientific Publishing Co.. https://doi.org/10.1142/9789813274884_0013

@inbook{9276d79f250c4d0484929ed0376aedff,

title = "Multilingual financial narrative processing: analyzing annual reports in English, Spanish, and Portuguese",

abstract = "This chapter describes and evaluates the use of information extraction (IE) and natural language processing (NLP) methods for extraction and analysis of financial annual reports in three languages: English, Spanish, and Portuguese. The work described retains information on document structure which is needed to enable a clear distinction between narrative and financial statement components of annual reports and between individual sections within the narratives component. Extraction accuracy varies between languages with English exceeding 95%. We apply the extraction methods on a comprehensive sample of annual reports published by UK, Spanish, and Portuguese non-financial firms between 2003 and 2014.",

author = "Mahmoud El-Haj and Paul Rayson and Paulo Alves and Carlos Herrero-Zorita and Steven Young",

note = "Publisher Copyright: {\textcopyright} 2019 by World Scientific Publishing Co. Pte. Ltd.",

year = "2019",

month = jan,

day = "1",

doi = "10.1142/9789813274884_0013",

language = "English",

isbn = "9789813274877",

pages = "441--463",

editor = "Marina Litvak and Natalia Vanetik",

booktitle = "Multilingual text analysis",

publisher = "World Scientific Publishing Co.",

address = "United States",

}

Multilingual financial narrative processing: analyzing annual reports in English, Spanish, and Portuguese. / El-Haj, Mahmoud; Rayson, Paul; Alves, Paulo et al.
Multilingual text analysis: challenges, models, and approaches. ed. / Marina Litvak; Natalia Vanetik. World Scientific Publishing Co., 2019. p. 441-463.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Multilingual financial narrative processing

T2 - analyzing annual reports in English, Spanish, and Portuguese

AU - El-Haj, Mahmoud

AU - Rayson, Paul

AU - Alves, Paulo

AU - Herrero-Zorita, Carlos

AU - Young, Steven

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This chapter describes and evaluates the use of information extraction (IE) and natural language processing (NLP) methods for extraction and analysis of financial annual reports in three languages: English, Spanish, and Portuguese. The work described retains information on document structure which is needed to enable a clear distinction between narrative and financial statement components of annual reports and between individual sections within the narratives component. Extraction accuracy varies between languages with English exceeding 95%. We apply the extraction methods on a comprehensive sample of annual reports published by UK, Spanish, and Portuguese non-financial firms between 2003 and 2014.

AB - This chapter describes and evaluates the use of information extraction (IE) and natural language processing (NLP) methods for extraction and analysis of financial annual reports in three languages: English, Spanish, and Portuguese. The work described retains information on document structure which is needed to enable a clear distinction between narrative and financial statement components of annual reports and between individual sections within the narratives component. Extraction accuracy varies between languages with English exceeding 95%. We apply the extraction methods on a comprehensive sample of annual reports published by UK, Spanish, and Portuguese non-financial firms between 2003 and 2014.

UR - http://www.scopus.com/inward/record.url?scp=85096246240&partnerID=8YFLogxK

U2 - 10.1142/9789813274884_0013

DO - 10.1142/9789813274884_0013

M3 - Chapter

AN - SCOPUS:85096246240

SN - 9789813274877

SP - 441

EP - 463

BT - Multilingual text analysis

A2 - Litvak, Marina

A2 - Vanetik, Natalia

PB - World Scientific Publishing Co.

ER -

Multilingual financial narrative processing: analyzing annual reports in English, Spanish, and Portuguese

Abstract

Access to Document

Other files and links

Fingerprint

Cite this