Projection-based Coreference Resolution Using Deep Syntax

Autor:	Michal Novák, Anna Nedoluzhko, Zdeněk Žabokrtský
Rok vydání:	2017
Předmět:	Coreference Syntax (programming languages) business.industry Computer science Resolution (logic) computer.software_genre language.human_language Task (project management) German Resolver language Artificial intelligence business Projection (set theory) computer Natural language processing
Zdroj:	Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017).
Popis:	The paper describes the system for coreference resolution in German and Russian, trained exclusively on coreference relations project ed through a parallel corpus from English. The resolver operates on the level of deep syntax and makes use of multiple specialized models. It achieves 32 and 22 points in terms of CoNLL score for Russian and German, respectively. Analysis of the evaluation results show that the resolver for Russian is able to preserve 66% of the English resolver’s quality in terms of CoNLL score. The system was submitted to the Closed track of the CORBON 2017 Shared task.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::30da7356e1552087c8b52d8fd808bb3d https://doi.org/10.18653/v1/w17-1508 Zobrazit plný text záznamu