XplaiNLI : Explainable Natural Language Inference through Visual Analytics

Kalouli, Aikaterini-Lida; Sevastjanova, Rita; de Paiva, Valeria; Crouch, Richard; El-Assady, Mennatallah

XplaiNLI : Explainable Natural Language Inference through Visual Analytics

Files

Kalouli_2-1io2p3cckids5.pdf(453.18 KB)

Date

2020

Authors

Kalouli, Aikaterini-Lida

Sevastjanova, Rita

de Paiva, Valeria

Crouch, Richard

El-Assady, Mennatallah

Publication type

Contribution to a conference collection

Publication status

Published

Published in

Proceedings of the 28th International Conference on Computational Linguistics : System Demonstrations / Ptaszynski, Michal; Ziolko, Bartosz (ed.). - Stroudsburg, PA : ACL, 2020. - pp. 48-52. - ISBN 978-1-952148-28-6

Abstract

Advances in Natural Language Inference (NLI) have helped us understand what state-of-the-art models really learn and what their generalization power is. Recent research has revealed some heuristics and biases of these models. However, to date, there is no systematic effort to capitalize on those insights through a system that uses these to explain the NLI decisions. To this end, we propose XplaiNLI, an eXplainable, interactive, visualization interface that computes NLI with different methods and provides explanations for the decisions made by the different approaches.

Subject (DDC)

004 Computer Science

Conference

28th International Conference on Computational Linguistics : System Demonstrations, Dec 8, 2020 - Dec 13, 2020, Barcelona

Cite This

ISO 690

KALOULI, Aikaterini-Lida, Rita SEVASTJANOVA, Valeria DE PAIVA, Richard CROUCH, Mennatallah EL-ASSADY, 2020. XplaiNLI : Explainable Natural Language Inference through Visual Analytics. 28th International Conference on Computational Linguistics : System Demonstrations. Barcelona, Dec 8, 2020 - Dec 13, 2020. In: PTASZYNSKI, Michal, ed., Bartosz ZIOLKO, ed.. Proceedings of the 28th International Conference on Computational Linguistics : System Demonstrations. Stroudsburg, PA:ACL, pp. 48-52. ISBN 978-1-952148-28-6

BibTex

@inproceedings{Kalouli2020Xplai-53009,
  year={2020},
  title={XplaiNLI : Explainable Natural Language Inference through Visual Analytics},
  url={https://www.aclweb.org/anthology/2020.coling-demos.9/},
  isbn={978-1-952148-28-6},
  publisher={ACL},
  address={Stroudsburg, PA},
  booktitle={Proceedings of the 28th International Conference on Computational Linguistics : System Demonstrations},
  pages={48--52},
  editor={Ptaszynski, Michal and Ziolko, Bartosz},
  author={Kalouli, Aikaterini-Lida and Sevastjanova, Rita and de Paiva, Valeria and Crouch, Richard and El-Assady, Mennatallah}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/53009">
    <dcterms:abstract xml:lang="eng">Advances in Natural Language Inference (NLI) have helped us understand what state-of-the-art models really learn and what their generalization power is. Recent research has revealed some heuristics and biases of these models. However, to date, there is no systematic effort to capitalize on those insights through a system that uses these to explain the NLI decisions. To this end, we propose XplaiNLI, an eXplainable, interactive, visualization interface that computes NLI with different methods and provides explanations for the decisions made by the different approaches.</dcterms:abstract>
    <dc:creator>Sevastjanova, Rita</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-02-26T09:02:34Z</dc:date>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Kalouli, Aikaterini-Lida</dc:contributor>
    <dc:creator>Crouch, Richard</dc:creator>
    <dcterms:title>XplaiNLI : Explainable Natural Language Inference through Visual Analytics</dcterms:title>
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <dc:contributor>Sevastjanova, Rita</dc:contributor>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53009/1/Kalouli_2-1io2p3cckids5.pdf"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53009/1/Kalouli_2-1io2p3cckids5.pdf"/>
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dc:creator>de Paiva, Valeria</dc:creator>
    <dc:creator>Kalouli, Aikaterini-Lida</dc:creator>
    <dc:contributor>Crouch, Richard</dc:contributor>
    <dcterms:issued>2020</dcterms:issued>
    <dc:contributor>de Paiva, Valeria</dc:contributor>
    <dc:language>eng</dc:language>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/53009"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-02-26T09:02:34Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
  </rdf:Description>
</rdf:RDF>

URL of original publication

https://www.aclweb.org/anthology/2020.coling-demos.9/

Test date of URL

2020-12-15

Bibliography of Konstanz

Yes