@inproceedings{el-haj-ogden-2022-financial,
title = "Financial Narrative Summarisation Using a Hybrid {TF}-{IDF} and Clustering Summariser: {AO}-Lancs System at {FNS} 2022",
author = "El-Haj, Mahmoud and
Ogden, Andrew",
editor = "El-Haj, Mahmoud and
Rayson, Paul and
Zmandar, Nadhem",
booktitle = "Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.fnp-1.11/",
pages = "79--82",
abstract = "This paper describes the HTAC system submitted to the Financial Narrative Summarization Shared Task (FNS-2022). A methodology implementing Financial narrative Processing (FNP) to summarise financial annual reports, named Hybrid TF-IDF and Clustering (HTAC). This involves a hybrid approach combining TF-IDF sentence ranking as an NLP tool with a state-of-the-art Clustering Machine learning model to produce short 1000-word summaries of long financial annual reports. These Annual Reports are a legal responsibility of public companies and are in excess of 50,000 words. The model extracts the crucial information from these documents, discarding the extraneous content, leaving only the crucial information in a shorter, non-redundant summary. Producing summaries that are more effective than summaries produced by two pre-existing generic summarisers."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-haj-ogden-2022-financial">
<titleInfo>
<title>Financial Narrative Summarisation Using a Hybrid TF-IDF and Clustering Summariser: AO-Lancs System at FNS 2022</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">Andrew</namePart>
<namePart type="family">Ogden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadhem</namePart>
<namePart type="family">Zmandar</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>
</relatedItem>
<abstract>This paper describes the HTAC system submitted to the Financial Narrative Summarization Shared Task (FNS-2022). A methodology implementing Financial narrative Processing (FNP) to summarise financial annual reports, named Hybrid TF-IDF and Clustering (HTAC). This involves a hybrid approach combining TF-IDF sentence ranking as an NLP tool with a state-of-the-art Clustering Machine learning model to produce short 1000-word summaries of long financial annual reports. These Annual Reports are a legal responsibility of public companies and are in excess of 50,000 words. The model extracts the crucial information from these documents, discarding the extraneous content, leaving only the crucial information in a shorter, non-redundant summary. Producing summaries that are more effective than summaries produced by two pre-existing generic summarisers.</abstract>
<identifier type="citekey">el-haj-ogden-2022-financial</identifier>
<location>
<url>https://aclanthology.org/2022.fnp-1.11/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>79</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Financial Narrative Summarisation Using a Hybrid TF-IDF and Clustering Summariser: AO-Lancs System at FNS 2022
%A El-Haj, Mahmoud
%A Ogden, Andrew
%Y El-Haj, Mahmoud
%Y Rayson, Paul
%Y Zmandar, Nadhem
%S Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F el-haj-ogden-2022-financial
%X This paper describes the HTAC system submitted to the Financial Narrative Summarization Shared Task (FNS-2022). A methodology implementing Financial narrative Processing (FNP) to summarise financial annual reports, named Hybrid TF-IDF and Clustering (HTAC). This involves a hybrid approach combining TF-IDF sentence ranking as an NLP tool with a state-of-the-art Clustering Machine learning model to produce short 1000-word summaries of long financial annual reports. These Annual Reports are a legal responsibility of public companies and are in excess of 50,000 words. The model extracts the crucial information from these documents, discarding the extraneous content, leaving only the crucial information in a shorter, non-redundant summary. Producing summaries that are more effective than summaries produced by two pre-existing generic summarisers.
%U https://aclanthology.org/2022.fnp-1.11/
%P 79-82
Markdown (Informal)
[Financial Narrative Summarisation Using a Hybrid TF-IDF and Clustering Summariser: AO-Lancs System at FNS 2022](https://aclanthology.org/2022.fnp-1.11/) (El-Haj & Ogden, FNP 2022)
ACL