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/ https://www.aclweb.o...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://www.aclweb.org/antholo...
Article
License: CC BY
Data sources: UnpayWall
https://doi.org/10.18653/v1/p1...
Article . 2017 . Peer-reviewed
Data sources: Crossref
https://dx.doi.org/10.60692/nq...
Other literature type . 2017
Data sources: Datacite
https://dx.doi.org/10.60692/96...
Other literature type . 2017
Data sources: Datacite
DBLP
Conference object
Data sources: DBLP
versions View all 4 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.

Semantic Dependency Parsing via Book Embedding

تحليل التبعية الدلالية عبر تضمين الكتاب
Authors: Weiwei Sun; Junjie Cao; Xiaojun Wan;

Semantic Dependency Parsing via Book Embedding

Abstract

Nous modélisons un graphe de dépendance comme un livre, un type particulier d'espace topologique, pour l'analyse de dépendance sémantique. La colonne vertébrale du livre est composée d'une séquence de mots, et chaque page contient un sous-ensemble d'arcs non croisés. Pour construire un graphe sémantique pour une phrase donnée, nous concevons de nouveaux algorithmes Maximum Subgraph pour générer des graphes non croisés sur chaque page, et un algorithme basé sur la relaxation lagrangienne pour combiner des pages dans un livre. Les expériences démontrent l'efficacité du cadre d'intégration du livre dans un large éventail de conditions. Notre analyseur obtient des résultats comparables avec un analyseur basé sur la transition de pointe.

Modelamos un gráfico de dependencia como un libro, un tipo particular de espacio topológico, para el análisis de dependencia semántica. La columna vertebral del libro se compone de una secuencia de palabras, y cada página contiene un subconjunto de arcos no cruzados. Para construir un gráfico semántico para una oración dada, diseñamos nuevos algoritmos de Maximum Subgraph para generar gráficos no cruzados en cada página, y un algoritmo basado en Lagrangian Relaxation para combinar páginas en un libro. Los experimentos demuestran la efectividad del marco de incrustación de libros en una amplia gama de condiciones. Nuestro analizador obtiene resultados comparables con un analizador basado en transición de última generación.

We model a dependency graph as a book, a particular kind of topological space, for semantic dependency parsing.The spine of the book is made up of a sequence of words, and each page contains a subset of noncrossing arcs.To build a semantic graph for a given sentence, we design new Maximum Subgraph algorithms to generate noncrossing graphs on each page, and a Lagrangian Relaxation-based algorithm to combine pages into a book.Experiments demonstrate the effectiveness of the book embedding framework across a wide range of conditions.Our parser obtains comparable results with a state-of-the-art transition-based parser.

نقوم بنمذجة رسم بياني للتبعية ككتاب، وهو نوع معين من الفضاء الطوبولوجي، لتحليل التبعية الدلالية. يتكون العمود الفقري للكتاب من سلسلة من الكلمات، وتحتوي كل صفحة على مجموعة فرعية من الأقواس غير المتقاطعة. لبناء رسم بياني دلالي لجملة معينة، نقوم بتصميم خوارزميات جديدة للحد الأقصى للرسم البياني الفرعي لإنشاء رسوم بيانية غير متقاطعة في كل صفحة، وخوارزمية قائمة على الاسترخاء في لاغرانج لدمج الصفحات في كتاب. توضح التجارب فعالية إطار تضمين الكتاب عبر مجموعة واسعة من الشروط. يحصل محللنا على نتائج قابلة للمقارنة مع محلل قائم على الانتقال الحديث.

Related Organizations
Keywords

Syntax-based Translation Models, Artificial intelligence, Sentence, Schema Matching, Graph, Theoretical computer science, Artificial Intelligence, Natural Language Processing, Semantic Web, Parsing, Natural language processing, Word Representation, Statistical Machine Translation and Natural Language Processing, Dependency grammar, Computer science, Dependency Parsing, Computer Science, Physical Sciences, Dependency (UML), Semantic Web and Ontology Development, Embedding

  • 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).
    5
    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.
    Average
    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!
5
Average
Average
Average
hybrid