251. Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings
- Author
-
Buzhou Tang, Bofang Li, Anna Rogers, Aleksandr Drozd, Xiaoyong Du, Tao Liu, and Zhe Zhao
- Subjects
Word embedding ,Computer science ,business.industry ,Context (language use) ,02 engineering and technology ,010501 environmental sciences ,computer.software_genre ,01 natural sciences ,Syntax ,Code (semiotics) ,Task (project management) ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,Representation (mathematics) ,business ,computer ,Word (computer architecture) ,Natural language processing ,0105 earth and related environmental sciences - Abstract
The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.