Bilingual Embeddings with Random Walks over Multilingual Wordnets

Autor: Goikoetxea, J., Soroa, A., Agirre, E.

Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then map them usi

Externí odkaz: http://arxiv.org/abs/1804.08316

Interpretable Semantic Textual Similarity: Finding and explaining differences between sentences

Autor: Lopez-Gazpio, I., Maritxalar, M., Gonzalez-Agirre, A., Rigau, G., Uria, L., Agirre, E.

User acceptance of artificial intelligence agents might depend on their ability to explain their reasoning, which requires adding an interpretability layer that fa- cilitates users to understand their behavior. This paper focuses on adding an in- ter

Externí odkaz: http://arxiv.org/abs/1612.04868

Learning class-to-class selectional preferences

Autor: Agirre, E., Martinez, D.

Publikováno v: Proceedings of the Workshop "Computational Natural Language Learning" (CoNLL-2001). In conjunction with ACL'2001/EACL'2001. Toulouse, France. 6-7th July 2001

Selectional preference learning methods have usually focused on word-to-class relations, e.g., a verb selects as its subject a given nominal class. This papers extends previous statistical models to class-to-class preferences, and presents a model th

Externí odkaz: http://arxiv.org/abs/cs/0109029

Interpretable semantic textual similarity: Finding and explaining differences between sentences

Autor: Lopez-Gazpio, I., Maritxalar, M., Gonzalez-Agirre, A., Rigau, G., Uria, L., Agirre, E.

Publikováno v: In Knowledge-Based Systems 1 March 2017 119:186-199

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.