Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ arXiv.org e-Print Ar...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
https://doi.org/10.18653/v1/20...
Article . 2022 . Peer-reviewed
Data sources: Crossref
https://dx.doi.org/10.60692/pq...
Other literature type . 2022
Data sources: Datacite
https://dx.doi.org/10.48550/ar...
Article . 2022
License: arXiv Non-Exclusive Distribution
Data sources: Datacite
https://dx.doi.org/10.60692/45...
Other literature type . 2022
Data sources: Datacite
versions View all 5 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Entailment Graph Learning with Textual Entailment and Soft Transitivity

تعلم الرسم البياني للاستحواذ مع الاستحواذ النصي والعبورية الناعمة
Authors: Zhibin Chen; Yue Feng; Dong Liang Zhao;

Entailment Graph Learning with Textual Entailment and Soft Transitivity

Abstract

Les graphiques d'implication typés essaient d'apprendre les relations d'implication entre les prédicats à partir du texte et de les modéliser en tant qu'arêtes entre les nœuds de prédicats. La construction des graphiques d'implication souffre généralement d'une grande rareté et d'un manque de fiabilité de la similitude distributionnelle. Nous proposons une méthode en deux étapes, le graphique d'implication avec implication textuelle et transitivité (EGT2) .EGT2 apprend les relations d'implication locales en reconnaissant l'implication textuelle possible entre les phrases modèles formées par les prédicats typés CCG-parsés. Sur la base du graphique local généré, EGT2 utilise ensuite trois nouvelles contraintes de transitivité douce pour considérer la transitivité logique dans les structures d'implication. Les expériences sur les ensembles de données de référence montrent qu'EGT2 peut bien modéliser la transitivité dans le graphique d'implication pour atténuer le problème de la rareté et conduire à une amélioration significative par rapport aux méthodes actuelles de l'état de la technique 1 .

Los gráficos de vinculación mecanografiados intentan aprender las relaciones de vinculación entre predicados a partir del texto y modelarlos como aristas entre nodos de predicados. La construcción de gráficos de vinculación generalmente sufre de una severa escasez y falta de confiabilidad de la similitud distributiva. Proponemos un método de dos etapas, Entailment Graph with Textual Entailment and Transitivity (EGT2). EGT2 aprende las relaciones de vinculación locales reconociendo la posible vinculación textual entre oraciones de plantilla formadas por predicados analizados por CCG mecanografiados. Sobre la base del gráfico local generado, EGT2 utiliza tres nuevas restricciones de transitividad suave para considerar la transitividad lógica en las estructuras de vinculación. Los experimentos en conjuntos de datos de referencia muestran que EGT2 puede modelar bien la transitividad en el gráfico de vinculación para aliviar el problema de la dispersión y conducir a una mejora significativa con respecto a los métodos actuales de vanguardia 1 .

Typed entailment graphs try to learn the entailment relations between predicates from text and model them as edges between predicate nodes.The construction of entailment graphs usually suffers from severe sparsity and unreliability of distributional similarity.We propose a two-stage method, Entailment Graph with Textual Entailment and Transitivity (EGT2).EGT2 learns local entailment relations by recognizing possible textual entailment between template sentences formed by typed CCG-parsed predicates.Based on the generated local graph, EGT2 then uses three novel soft transitivity constraints to consider the logical transitivity in entailment structures.Experiments on benchmark datasets show that EGT2 can well model the transitivity in entailment graph to alleviate the sparsity issue, and lead to significant improvement over current state-of-the-art methods 1 .

تحاول مخططات التضمين المطبوعة معرفة علاقات التضمين بين المسندات من النص ونمذجتها كحواف بين العقد المسندة. عادة ما يعاني بناء مخططات التضمين من تباين شديد وعدم موثوقية التشابه التوزيعي. نقترح طريقة من مرحلتين، مخطط التضمين مع التضمين النصي والعبور (EGT2). يتعلم EGT2 علاقات التضمين المحلية من خلال التعرف على التضمين النصي المحتمل بين جمل القوالب التي شكلتها المسندات الموزعة على CCG المكتوبة. بناءً على الرسم البياني المحلي الذي تم إنشاؤه، يستخدم EGT2 بعد ذلك ثلاثة قيود انتقالية ناعمة جديدة للنظر في العبور المنطقي في هياكل التضمين. تظهر التجارب على مجموعات البيانات المعيارية أن EGT2 يمكن أن يكون نموذجًا جيدًا للعبور في الرسم البياني للتخفيف من مشكلة التباين، ويؤدي إلى تحسن كبير في الأساليب الحديثة الحالية 1 .

Related Organizations
Keywords

FOS: Computer and information sciences, Parsing, Logical consequence, Textual entailment, Artificial intelligence, Computer Science - Computation and Language, Topic Modeling, Natural language processing, Statistical Machine Translation and Natural Language Processing, Computer science, Text Simplification, Artificial Intelligence, Combinatorics, Computer Science, Physical Sciences, Semantic Simplification, FOS: Mathematics, Automatic Text Simplification and Readability Assessment, Computation and Language (cs.CL), Transitive relation, Mathematics, Natural Language Processing

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    4
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
4
Top 10%
Average
Average
Green