|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ЦЭМИ РАН |
||
Domain-specific Taxonomy Enrichment based on Meta-Embeddingsстатья
- Авторы: Tikhomirov Mikhail, Loukachevitch Natalia V.
- Сборник: CEUR Workshop Proceedings
- Серия: Proceedings of the XXIII International Conference on Data Analytics and Management in Data Intensive Domains (DAMDID/RCDL 2021)
- Том: 3036
- Год издания: 2021
- Первая страница: 285
- Последняя страница: 298
- Аннотация: In this paper we study the use of meta-embeddings approaches, which combine several source embeddings, for the taxonomy class prediction of new terms. We test the proposed approach in the informationsecurity domain in the task of enriching the Ontology on Natural Sciences and technologies (OENT). We show that autoencoder-based metaembeddings with triplet loss achieve the best results in the task. The highest results are obtained on combination of in domain and out-ofdomain embeddings.
- Добавил в систему: Тихомиров Михаил Михайлович