Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures

<p dir="ltr">An interesting aspect of structured prediction is the evaluation of an output structure against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely limited the expressivity of effective loss functions...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Iryna Haponchyk (19691701) (author)
مؤلفون آخرون: Alessandro Moschitti (19691683) (author)
منشور في: 2017
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513557090009088
author Iryna Haponchyk (19691701)
author2 Alessandro Moschitti (19691683)
author2_role author
author_facet Iryna Haponchyk (19691701)
Alessandro Moschitti (19691683)
author_role author
dc.creator.none.fl_str_mv Iryna Haponchyk (19691701)
Alessandro Moschitti (19691683)
dc.date.none.fl_str_mv 2017-07-30T06:00:00Z
dc.identifier.none.fl_str_mv 10.18653/v1/p17-1094
dc.relation.none.fl_str_mv https://figshare.com/articles/conference_contribution/Don_t_understand_a_measure_Learn_it_Structured_Prediction__for_Coreference_Resolution_optimizing_its_measures/27050743
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
Output Structure Evaluation
Gold Standard
Loss-Augmented Setting
Max-Violating Constraint
Expressive Loss Functions
Coreference Resolution
dc.title.none.fl_str_mv Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
dc.type.none.fl_str_mv Text
Conference contribution
info:eu-repo/semantics/publishedVersion
text
conference object
description <p dir="ltr">An interesting aspect of structured prediction is the evaluation of an output structure against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely limited the expressivity of effective loss functions. In this paper, we trade off exact computation for enabling the use and study of more complex loss functions for coreference resolution. Most interestingly, we show that such functions can be (i) automatically learned also from controversial but commonly accepted coreference measures, e.g., MELA, and (ii) successfully used in learning algorithms. The accurate model comparison on the standard CoNLL-2012 setting shows the benefit of more expressive loss functions.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<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/p17-1094" target="_blank">https://dx.doi.org/10.18653/v1/p17-1094</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017</p>
eu_rights_str_mv openAccess
id Manara2_8024f94118363657924658425ee450e2
identifier_str_mv 10.18653/v1/p17-1094
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27050743
publishDate 2017
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measuresIryna Haponchyk (19691701)Alessandro Moschitti (19691683)Information and computing sciencesArtificial intelligenceMachine learningLanguage, communication and cultureLinguisticsOutput Structure EvaluationGold StandardLoss-Augmented SettingMax-Violating ConstraintExpressive Loss FunctionsCoreference Resolution<p dir="ltr">An interesting aspect of structured prediction is the evaluation of an output structure against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely limited the expressivity of effective loss functions. In this paper, we trade off exact computation for enabling the use and study of more complex loss functions for coreference resolution. Most interestingly, we show that such functions can be (i) automatically learned also from controversial but commonly accepted coreference measures, e.g., MELA, and (ii) successfully used in learning algorithms. The accurate model comparison on the standard CoNLL-2012 setting shows the benefit of more expressive loss functions.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<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/p17-1094" target="_blank">https://dx.doi.org/10.18653/v1/p17-1094</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017</p>2017-07-30T06:00:00ZTextConference contributioninfo:eu-repo/semantics/publishedVersiontextconference object10.18653/v1/p17-1094https://figshare.com/articles/conference_contribution/Don_t_understand_a_measure_Learn_it_Structured_Prediction__for_Coreference_Resolution_optimizing_its_measures/27050743CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/270507432017-07-30T06:00:00Z
spellingShingle Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
Iryna Haponchyk (19691701)
Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
Output Structure Evaluation
Gold Standard
Loss-Augmented Setting
Max-Violating Constraint
Expressive Loss Functions
Coreference Resolution
status_str publishedVersion
title Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
title_full Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
title_fullStr Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
title_full_unstemmed Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
title_short Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
title_sort Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
topic Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
Output Structure Evaluation
Gold Standard
Loss-Augmented Setting
Max-Violating Constraint
Expressive Loss Functions
Coreference Resolution