Paper: Unsupervised All-words Word Sense Disambiguation with Grammatical Dependencies

ACL ID I08-2105
Title Unsupervised All-words Word Sense Disambiguation with Grammatical Dependencies
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2008
Authors

We present experiments that analyze the necessity of using a highly interconnected word/sense graph for unsupervised all- words word sense disambiguation. We show that allowing only grammatically related words to in uence each other’s senses leads to disambiguation results on a par with the best graph-based systems, while greatly re- ducing the computation load. We also com- pare two methods for computing selectional preferences between the senses of every two grammatically related words: one using a Lesk-based measure on WordNet, the other using dependency relations from the British National Corpus. The best con guration uses the syntactically-constrained graph, se- lectional preferences computed from the corpus and a PageRank tie-breaking algo- rithm. We especially note good performanc...