—Typical information extraction (IE) systems can be seen as tasks assigning labels to words in a natural language sequence. The performance is restricted by the availability of l...
Yanjun Qi, Pavel Kuksa, Ronan Collobert, Kunihiko ...
Internet users regularly have the need to find biographies and facts of people of interest. Wikipedia has become the first stop for celebrity biographies and facts. However, Wik...
Xiaojiang Liu, Zaiqing Nie, Nenghai Yu, Ji-Rong We...
Most information extraction systems either use hand written extraction patterns or use a machine learning algorithm that is trained on a manually annotated corpus. Both of these a...
This paper deals with an acronym/definition extraction approach from textual data (corpora) and the disambiguation of these definitions (or expansions). Both steps of our global pr...
Coreference resolution is a classic NLP problem and has been studied extensively by many researchers. Most existing studies, however, are generic in the sense that they are not fo...