Yuanzhi Ke

Learn More
We figure out a trap that is not carefully addressed in the previous works using lexicons or ontologies to train or improve distributed word representations: For pol-ysemous words and utterances changing meaning in different contexts, their paraphrases or related entities in a lexicon or an ontology are unreliable and sometimes deteriorate the learning of(More)
—Though there are some works on improving distributed word representations using lexicons, the improper over-fitting of the words that have multiple meanings is a remaining issue deteriorating the learning when lexicons are used, which needs to be solved. An alternative method is to allocate a vector per sense instead a vector per word. However, the word(More)
  • 1