Extracting knowledge from unstructured text is a long-standing goal of NLP. Although learning approaches to many of its subtasks have been developed (e.g., parsing, taxonomy induc...
Bloom filters make use of a "probabilistic" hash-coding method to reduce the amount of space required to store a hash set. A Bloom filter offers a trade-off between its ...
Mark C. Little, Santosh K. Shrivastava, Neil A. Sp...
Previous research has demonstrated the importance of handling differences between domains such as "newswire" and "biomedicine" when porting NLP systems from on...
Temporal expressions in texts contain significant temporal information. Understanding temporal information is very useful in many NLP applications, such as information extraction,...
This paper demonstrates a conceptually simple but effective method of increasing the accuracy of QA systems on factoid-style questions. We define the notion of an inverted questio...