Back to Search
Start Over
$K$-Embeddings: Learning Conceptual Embeddings for Words using Context
- Source :
- HLT-NAACL
- Publication Year :
- 2016
- Publisher :
- Association for Computational Linguistics, 2016.
-
Abstract
- We describe a technique for adding contextual distinctions to word embeddings by extending the usual embedding process — into two phases. The first phase resembles existing methods, but also constructs K classifications of concepts. The second phase uses these classifications in developing refined K embeddings for words, namely word K-embeddings. The technique is iterative, scalable, and can be combined with other methods (including Word2Vec) in achieving still more expressive representations. Experimental results show consistently large performance gains on a Semantic-Syntactic Word Relationship test set for different K settings. For example, an overall gain of 20% is recorded at K = 5. In addition, we demonstrate that an iterative process can further tune the embeddings and gain an extra 1% (K = 10 in 3 iterations) on the same benchmark. The examples also show that polysemous concepts are meaningfully embedded in our K different conceptual embeddings for words.
- Subjects :
- Embedding process
Theoretical computer science
Computer science
Context (language use)
02 engineering and technology
010501 environmental sciences
01 natural sciences
020204 information systems
Test set
0202 electrical engineering, electronic engineering, information engineering
Benchmark (computing)
Word2vec
Algorithm
Word (computer architecture)
0105 earth and related environmental sciences
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Accession number :
- edsair.doi...........f49081b86bd95f9f10efd25cc21695e7