Re:Word embeddings in 2017: Trends and future directions
by nl on Sunday October 22, 2017 @06:00AM
(#15525961)
Word vectors are "useful" as an alternative representation for words in any machine learning task.
Previously one used TF-IDF to represent a document, but now one uses Word2Vec and will usually get better results.
For example, From Word Embeddings To Document Distances[1] shows how to use a new distance measure (Word Mover Distance) in classification tasks. This leads to state-of-the-art performance on 6 out of 8 classic text classification datasets (and very close on the other 2).
In most other practical NLP tasks you find similar results: replacing an older representation with a word embedding almost always improves performance.
Previously one used TF-IDF to represent a document, but now one uses Word2Vec and will usually get better results.
For example, From Word Embeddings To Document Distances[1] shows how to use a new distance measure (Word Mover Distance) in classification tasks. This leads to state-of-the-art performance on 6 out of 8 classic text classification datasets (and very close on the other 2).
In most other practical NLP tasks you find similar results: replacing an older representation with a word embedding almost always improves performance.
[1] http://proceedings.mlr.press/v37/kusnerb15.pdf