no code implementations • WS 2018 • Marzena Karpinska, Bofang Li, Anna Rogers, Aleks Drozd, R
Languages with logographic writing systems present a difficulty for traditional character-level models.
no code implementations • WS 2018 • Bofang Li, Aleks Drozd, R, Tao Liu, Xiaoyong Du
Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries.
no code implementations • EMNLP 2017 • Bofang Li, Tao Liu, Zhe Zhao, Buzhou Tang, Aleks Drozd, R, Anna Rogers, Xiaoyong Du
The number of word embedding models is growing every year.
no code implementations • SEMEVAL 2017 • Anna Rogers, Aleks Drozd, R, Bofang Li
This paper explores the possibilities of analogical reasoning with vector space models.
no code implementations • COLING 2016 • Aleks Drozd, R, Anna Gladkova, Satoshi Matsuoka
Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as \textit{king}:\textit{man} :: \textit{woman}:\textit{queen}) are indicative of the quality of the embedding.