Papers by Dongsuk O
Word Sense Disambiguation Based on Word Similarity Calculation Using Word Vector Representation from a Knowledge-based Graph (C18-1)
Copied to clipboard
| Challenge: | Existing methods to determine the word sense have fewer word set constraints than unsupervised methods. |
| Approach: | They propose a new word sense disambiguation method that generates the context of an ambiguous word by using similarities between an amorphous word and words in the input document. |
| Outcome: | The proposed method outperforms the baseline method on the SemEval-13 and SemEx15 datasets and has higher performance than the state-of-the-art unsupervised knowledge-based system. |