<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pant-chopra-2022-multilingual">
    <titleInfo>
        <title>Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Manish</namePart>
        <namePart type="family">Pant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ankush</namePart>
        <namePart type="family">Chopra</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 multi-lingual long document summarization systems submitted to the Financial Narrative Summarization Shared Task (FNS 2022 ) by Team-Tredence. We developed task-specific summarization methods for 3 languages – English, Spanish and Greek. The solution is divided into two parts, where a RoBERTa model was finetuned to identify/extract summarizing segments from English documents and T5 based models were used for summarizing Spanish and Greek documents. A purely extractive approach was applied to summarize English documents using data-specific heuristics. An mT5 model was fine-tuned to identify potential narrative sections for Greek and Spanish, followed by finetuning mT5 and T5(Spanish version) for abstractive summarization task. This system also features a novel approach for generating summarization training dataset using long document segmentation and the semantic similarity across segments. We also introduce an N-gram variability score to select sub-segments for generating more diverse and informative summaries from long documents.</abstract>
    <identifier type="citekey">pant-chopra-2022-multilingual</identifier>
    <location>
        <url>https://aclanthology.org/2022.fnp-1.18</url>
    </location>
    <part>
        <date>2022-06</date>
        <extent unit="page">
            <start>112</start>
            <end>115</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022
%A Pant, Manish
%A Chopra, Ankush
%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 pant-chopra-2022-multilingual
%X This paper describes multi-lingual long document summarization systems submitted to the Financial Narrative Summarization Shared Task (FNS 2022 ) by Team-Tredence. We developed task-specific summarization methods for 3 languages – English, Spanish and Greek. The solution is divided into two parts, where a RoBERTa model was finetuned to identify/extract summarizing segments from English documents and T5 based models were used for summarizing Spanish and Greek documents. A purely extractive approach was applied to summarize English documents using data-specific heuristics. An mT5 model was fine-tuned to identify potential narrative sections for Greek and Spanish, followed by finetuning mT5 and T5(Spanish version) for abstractive summarization task. This system also features a novel approach for generating summarization training dataset using long document segmentation and the semantic similarity across segments. We also introduce an N-gram variability score to select sub-segments for generating more diverse and informative summaries from long documents.
%U https://aclanthology.org/2022.fnp-1.18
%P 112-115

Markdown (Informal)

[Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022](https://aclanthology.org/2022.fnp-1.18) (Pant & Chopra, FNP 2022)

• Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022 (Pant & Chopra, FNP 2022)

ACL

• Manish Pant and Ankush Chopra. 2022. Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022. In Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022, pages 112–115, Marseille, France. European Language Resources Association.