We tackle the problem of automatically detecting controversial issues and their subtopics from news articles. We define a controversial issue as a concept that invokes conflicting ...
This paper summarizes and compares techniques for detecting and identifying markers in the context of computer vision. Existing approaches use correlation, digital, or topological...
The goal of our research is to improve event extraction by learning to identify secondary role filler contexts in the absence of event keywords. We propose a multilayered event e...
This work provides algorithms and heuristics to index text documents by determining important topics in the documents. To index text documents, the work provides algorithms to gene...
Contradiction Detection (CD) in text is a difficult NLP task. We investigate CD over functions (e.g., BornIn(Person)=Place), and present a domain-independent algorithm that automa...
Alan Ritter, Stephen Soderland, Doug Downey, Oren ...