Results 41 to 50 of about 2,539,338 (202)

Approaches to Anaphora Resolution in a Natural Language Database Management System

open access: yesKansas Working Papers in Linguistics, 1986
This paper describes in detail the computational process of finding the non-indexical linguistic objects to which pronoun anaphoras resolve. The successful development of discrete steps for anaphora resolution is critical for any natural language ...
Nara, Hiroshi
doaj   +1 more source

Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning

open access: yesConference on Empirical Methods in Natural Language Processing, 2021
Parallel texts of Japanese and a non-pro-drop language have the potential of improving the performance of Japanese zero anaphora resolution (ZAR) because pronouns dropped in the former are usually mentioned explicitly in the latter.
Masato Umakoshi   +2 more
semanticscholar   +1 more source

Neural Anaphora Resolution in Dialogue

open access: yesCODI, 2021
We describe the systems that we developed for the three tracks of the CODI-CRAC 2021 shared task, namely entity coreference resolution, bridging resolution, and discourse deixis resolution.
Hideo Kobayashi, Shengjie Li, Vincent Ng
semanticscholar   +1 more source

Mehr: A Persian Coreference Resolution Corpus [PDF]

open access: yesJournal of Artificial Intelligence and Data Mining, 2023
Coreference resolution is one of the essential tasks of natural languageprocessing. This task identifies all in-text expressions that refer to thesame entity in the real world. Coreference resolution is used in otherfields of natural language processing,
Hassan Haji Mohammadi   +3 more
doaj   +1 more source

Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution [PDF]

open access: yesInternational Conference on Computational Linguistics, 2020
Now that the performance of coreference resolvers on the simpler forms of anaphoric reference has greatly improved, more attention is devoted to more complex aspects of anaphora.
Juntao Yu   +3 more
semanticscholar   +1 more source

Real Anaphora Resolution Is Hard [PDF]

open access: yes, 2010
We introduce a system for anaphora resolution for German that uses various resources in order to develop a real system as opposed to systems based on idealized assumptions, e.g. the use of true mentions only or perfect parse trees and perfect morphology.
Klenner, M, Fahrni, A, Sennrich, R
openaire   +2 more sources

Context-Aware Neural Machine Translation Learns Anaphora Resolution [PDF]

open access: yesAnnual Meeting of the Association for Computational Linguistics, 2018
Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence.
Elena Voita   +3 more
semanticscholar   +1 more source

An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution [PDF]

open access: yesInternational Conference on Computational Linguistics, 2020
One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation.
Ryuto Konno   +5 more
semanticscholar   +1 more source

The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis Resolution in Dialogue: A Cross-Team Analysis

open access: yesCODI, 2021
The CODI-CRAC 2021 shared task is the first shared task that focuses exclusively on anaphora resolution in dialogue and provides three tracks, namely entity coreference resolution, bridging resolution, and discourse deixis resolution.
Shengjie Li, Hideo Kobayashi, Vincent Ng
semanticscholar   +1 more source

Transformer Attention vs Human Attention in Anaphora Resolution

open access: yesWorkshop on Cognitive Modeling and Computational Linguistics
Motivated by human cognitive processes, attention mechanism within transformer architecture has been developed to assist neural networks in allocating focus to specific aspects within input data.
Anastasia V. Kozlova   +4 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy