Titlebook: Natural Language Processing – IJCNLP 2004; First International Keh-Yih Su,Jun’ichi Tsujii,Oi Yee Kwong Conference proceedings 2005 Springe

ascend

BADGE

Iterative CKY Parsing for Probabilistic Context-Free Grammarss. Experimental results using the Penn Treebank II corpus show that the iterative CKY achieved more than 60% reduction of edges compared with the conventional CKY algorithm and the run-time overhead is very small. Our algorithm is general enough to incorporate a more sophisticated estimation function, which should lead to more efficient parsing.

Perennial長期的

A Novel Pattern Learning Method for Open Domain Question Answeringworthy that our method has been implemented automatically and it can handle the problem other system failed, and satisfactory results have been achieved. Finally, we give a performance analysis of this approach using the TREC-11 question set.

疏忽

Boycott

fructose

Combining Labeled and Unlabeled Data for Learning Cross-Document Structural Relationships documents, exploiting both labeled and unlabeled data. We investigate a binary classifier for determining existence of structural relationships and a full classifier using the full taxonomy of relationships. We show that in both cases the exploitation of unlabeled data helps improve the performance of learned classifiers.

DAFT

平常

熔巖

fixed-joint