RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations

<p dir="ltr">We present a highly-flexible UIMA-based pipeline for developing structural kernelbased systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For exa...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Kateryna Tymoshenko (19691680) (author)
مؤلفون آخرون: Alessandro Moschitti (19691683) (author), Massimo Nicosia (19691686) (author), Aliaksei Severyn (18370833) (author)
منشور في: 2017
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513557092106240
author Kateryna Tymoshenko (19691680)
author2 Alessandro Moschitti (19691683)
Massimo Nicosia (19691686)
Aliaksei Severyn (18370833)
author2_role author
author
author
author_facet Kateryna Tymoshenko (19691680)
Alessandro Moschitti (19691683)
Massimo Nicosia (19691686)
Aliaksei Severyn (18370833)
author_role author
dc.creator.none.fl_str_mv Kateryna Tymoshenko (19691680)
Alessandro Moschitti (19691683)
Massimo Nicosia (19691686)
Aliaksei Severyn (18370833)
dc.date.none.fl_str_mv 2017-07-30T06:00:00Z
dc.identifier.none.fl_str_mv 10.18653/v1/p17-4014
dc.relation.none.fl_str_mv https://figshare.com/articles/conference_contribution/RelTextRank_An_Open_Source_Framework_for_Building_Relational__Syntactic-Semantic_Text_Pair_Representations/27050725
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
UIMA
Pipeline
Structural kernel-based systems
Relational learning
Text processing
Training data
Test data
dc.title.none.fl_str_mv RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
dc.type.none.fl_str_mv Text
Conference contribution
info:eu-repo/semantics/publishedVersion
text
conference object
description <p dir="ltr">We present a highly-flexible UIMA-based pipeline for developing structural kernelbased systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For example, the proposed pipeline can represent an input question and answer sentence pairs as syntacticsemantic structures, enriching them with relational information, e.g., links between question class, focus and named entities, and serializes them as training and test files for the tree kernel-based reranking framework. The pipeline generates a number of dependency and shallow chunkbased representations shown to achieve competitive results in previous work. It also enables easy evaluation of the models thanks to cross-validation facilities.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of ACL 2017, System Demonstrations<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See conference contribution on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p17-4014" target="_blank">https://dx.doi.org/10.18653/v1/p17-4014</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations, Vancouver, Canada, July 30 - August 4, 2017<br></p>
eu_rights_str_mv openAccess
id Manara2_f2b58056da5e2147d080bbc9207a5790
identifier_str_mv 10.18653/v1/p17-4014
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27050725
publishDate 2017
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair RepresentationsKateryna Tymoshenko (19691680)Alessandro Moschitti (19691683)Massimo Nicosia (19691686)Aliaksei Severyn (18370833)Information and computing sciencesArtificial intelligenceMachine learningLanguage, communication and cultureLinguisticsUIMAPipelineStructural kernel-based systemsRelational learningText processingTraining dataTest data<p dir="ltr">We present a highly-flexible UIMA-based pipeline for developing structural kernelbased systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For example, the proposed pipeline can represent an input question and answer sentence pairs as syntacticsemantic structures, enriching them with relational information, e.g., links between question class, focus and named entities, and serializes them as training and test files for the tree kernel-based reranking framework. The pipeline generates a number of dependency and shallow chunkbased representations shown to achieve competitive results in previous work. It also enables easy evaluation of the models thanks to cross-validation facilities.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of ACL 2017, System Demonstrations<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See conference contribution on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p17-4014" target="_blank">https://dx.doi.org/10.18653/v1/p17-4014</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations, Vancouver, Canada, July 30 - August 4, 2017<br></p>2017-07-30T06:00:00ZTextConference contributioninfo:eu-repo/semantics/publishedVersiontextconference object10.18653/v1/p17-4014https://figshare.com/articles/conference_contribution/RelTextRank_An_Open_Source_Framework_for_Building_Relational__Syntactic-Semantic_Text_Pair_Representations/27050725CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/270507252017-07-30T06:00:00Z
spellingShingle RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
Kateryna Tymoshenko (19691680)
Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
UIMA
Pipeline
Structural kernel-based systems
Relational learning
Text processing
Training data
Test data
status_str publishedVersion
title RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
title_full RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
title_fullStr RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
title_full_unstemmed RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
title_short RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
title_sort RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations
topic Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
UIMA
Pipeline
Structural kernel-based systems
Relational learning
Text processing
Training data
Test data