We present a graph-based semi-supervised learning for the question-answering (QA) task for ranking candidate sentences. Using textual entailment analysis, we obtain entailment sco...
A plausible definition of "reasoning" could be "algebraically manipulating previously acquired knowledge in order to answer a new question". This definition co...
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...
We describe two corpora of question and answer pairs collected for complex, open-domain Question Answering (QA) to enable answer classification and re-ranking experiments. We deli...
Abstract. We analyze the expected cost of a greedy active learning algorithm. Our analysis extends previous work to a more general setting in which different queries have differe...