In this paper, we explore correlation of dependency relation paths to rank candidate answers in answer extraction. Using the correlation measure, we compare dependency relations o...
The paper analyzes both acoustic and linguistic features with different Chinese prosodic boundaries. Then a rule-learning approach was used to do the prosodic boundary labelling. ...
Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few see...
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...
Convolution kernels, such as tree kernel and subsequence kernel are useful for natural language processing tasks. However, most of them ignore the semantic knowledge. In order to ...