<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="passali-etal-2021-towards">
    <titleInfo>
        <title>Towards Human-Centered Summarization: A Case Study on Financial News</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tatiana</namePart>
        <namePart type="family">Passali</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexios</namePart>
        <namePart type="family">Gidiotis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Efstathios</namePart>
        <namePart type="family">Chatzikyriakidis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Grigorios</namePart>
        <namePart type="family">Tsoumakas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent Deep Learning (DL) summarization models greatly outperform traditional summarization methodologies, generating high-quality summaries. Despite their success, there are still important open issues, such as the limited engagement and trust of users in the whole process. In order to overcome these issues, we reconsider the task of summarization from a human-centered perspective. We propose to integrate a user interface with an underlying DL model, instead of tackling summarization as an isolated task from the end user. We present a novel system, where the user can actively participate in the whole summarization process. We also enable the user to gather insights into the causative factors that drive the model’s behavior, exploiting the self-attention mechanism. We focus on the financial domain, in order to demonstrate the efficiency of generic DL models for domain-specific applications. Our work takes a first step towards a model-interface co-design approach, where DL models evolve along user needs, paving the way towards human-computer text summarization interfaces.</abstract>
    <identifier type="citekey">passali-etal-2021-towards</identifier>
    <location>
        <url>https://aclanthology.org/2021.hcinlp-1.4</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>21</start>
            <end>27</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Human-Centered Summarization: A Case Study on Financial News
%A Passali, Tatiana
%A Gidiotis, Alexios
%A Chatzikyriakidis, Efstathios
%A Tsoumakas, Grigorios
%S Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F passali-etal-2021-towards
%X Recent Deep Learning (DL) summarization models greatly outperform traditional summarization methodologies, generating high-quality summaries. Despite their success, there are still important open issues, such as the limited engagement and trust of users in the whole process. In order to overcome these issues, we reconsider the task of summarization from a human-centered perspective. We propose to integrate a user interface with an underlying DL model, instead of tackling summarization as an isolated task from the end user. We present a novel system, where the user can actively participate in the whole summarization process. We also enable the user to gather insights into the causative factors that drive the model’s behavior, exploiting the self-attention mechanism. We focus on the financial domain, in order to demonstrate the efficiency of generic DL models for domain-specific applications. Our work takes a first step towards a model-interface co-design approach, where DL models evolve along user needs, paving the way towards human-computer text summarization interfaces.
%U https://aclanthology.org/2021.hcinlp-1.4
%P 21-27

Markdown (Informal)

[Towards Human-Centered Summarization: A Case Study on Financial News](https://aclanthology.org/2021.hcinlp-1.4) (Passali et al., HCINLP 2021)

• Towards Human-Centered Summarization: A Case Study on Financial News (Passali et al., HCINLP 2021)

ACL

• Tatiana Passali, Alexios Gidiotis, Efstathios Chatzikyriakidis, and Grigorios Tsoumakas. 2021. Towards Human-Centered Summarization: A Case Study on Financial News. In Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 21–27, Online. Association for Computational Linguistics.