Title | ||
---|---|---|
NUS-PT: exploiting parallel texts for word sense disambiguation in the English all-words tasks |
Abstract | ||
---|---|---|
We participated in the SemEval-2007 coarse-grained English all-words task and fine-grained English all-words task. We used a supervised learning approach with SVM as the learning algorithm. The knowledge sources used include local collocations, parts-of-speech, and surrounding words. We gathered training examples from English-Chinese parallel corpora, SemCor, and DSO corpus. While the fine-grained sense inventory of WordNet was used to train our system employed for the fine-grained English all-words task, our system employed for the coarse-grained English all-words task was trained with the coarse-grained sense inventory released by the task organizers. Our scores (for both recall and precision) are 0.825 and 0.587 for the coarse-grained English all-words task and fine-grained English all-words task respectively. These scores put our systems in the first place for the coarse-grained English all-words task and the second place for the fine-grained English all-words task. |
Year | Venue | Keywords |
---|---|---|
2007 | SemEval@ACL | word sense disambiguation,parallel text,task organizer,local collocation,dso corpus,coarse-grained sense inventory,fine-grained english all-words task,coarse-grained english all-words task,fine-grained sense inventory,knowledge source,supervised learning approach,english-chinese parallel corpus,col,part of speech,supervised learning |
Field | DocType | Citations |
Computer science,Support vector machine,Precision and recall,Parallel corpora,Supervised learning,Speech recognition,Natural language processing,Artificial intelligence,WordNet,Word-sense disambiguation | Conference | 54 |
PageRank | References | Authors |
2.87 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yee Seng Chan | 1 | 584 | 27.67 |
Hwee Tou Ng | 2 | 4092 | 300.40 |
Zhi Zhong | 3 | 232 | 8.96 |