Master Tesia
Tituloa:
A Common Semantic Space for Monolingual and Cross-Lingual Meta-Embeddings
Egilea:
Iker García Ferrero
Abstract:
This master’s thesis presents a new technique for creating monolingual and cross-lingual
meta-embeddings. Our method integrates multiple word embeddings created from com-
plementary techniques, textual sources, knowledge bases and languages. Existing word
vectors are projected to a common semantic space using linear transformations and aver-
aging. With our method the resulting meta-embeddings maintain the dimensionality of the
original embeddings without losing information while dealing with the out-of-vocabulary
(OOV) problem. Furthermore, empirical evaluation demonstrates the effectiveness of our
technique with respect to previous work on various intrinsic and extrinsic multilingual
evaluations.
Fitxategia:
Tutorea:
German Rigau i Claramunt
Urtea:
2019
Esleitua: