RENERSANs: RELATION EXTRACTION AND NAMED ENTITY RECOGNITION AS SEQUENCE ANNOTATION

Autor:	Ranepa, Moscow, Russia, Adis Davletov, Alexey Rey, Denis Gordeev, Nikolay Arefyev
Rok vydání:	2020
Předmět:	Named-entity recognition Sequence annotation business.industry Computer science Artificial intelligence business computer.software_genre Relationship extraction computer Natural language processing
Zdroj:	Computational Linguistics and Intellectual Technologies.
ISSN:	2075-7182
DOI:	10.28995/2075-7182-2020-19-187-197
Popis:	In this work we present our system for RuREBus shared task held together with Dialog 2020 conference. The task consisted of 3 subtasks: named entity recognition, relation extraction with provided named entity tags and end-to-end relation extraction. Our system took the first and the second place in the first and the second subtasks respectively. For the third subtask we submitted our solution only in the post-evaluation phase, however, it was among the top 2 best performing systems. The systems for all tasks are based on Transformer models. Relation extraction was solved as a sequence labelling problem. We also used joint task named entity and relation extraction learning.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fbc5baf63e8180aa072345c4a1f9c981 https://doi.org/10.28995/2075-7182-2020-19-187-197 Zobrazit plný text záznamu