All-but-the-Top: Simple and Effective Postprocessing for Word Representations
Mu, Jiaqi, Bhat, Suma, Viswanath, Pramod
Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a few top dominating directions from the word vectors -- that renders off-the-shelf representations {\em even stronger}. The postprocessing is empirically validated on a variety of lexical-level intrinsic tasks (word similarity, concept categorization, word analogy) and sentence-level tasks (semantic textural similarity and { text classification}) on multiple datasets and with a variety of representation methods and hyperparameter choices in multiple languages; in each case, the processed representations are consistently better than the original ones.
Mar-18-2018, 19:00:00 GMT
- Country:
- Europe (0.67)
- North America > United States
- Illinois (0.14)
- Genre:
- Research Report (0.82)
- Technology: