We use web-scale N-grams in a base NP parser that correctly analyzes 95.4% of the base NPs in natural text. Web-scale data improves performance. That is, there is no data like mor...
This paper presents an approach to summarize single scientific papers, by extracting its contributions from the set of citation sentences written in other papers. Our methodology ...
Main approaches to corpus-based semantic class mining include distributional similarity (DS) and pattern-based (PB). In this paper, we perform an empirical comparison of them, bas...
In this paper, we propose a method for mediatory summarization, which is a novel technique for facilitating users' assessments of the credibility of information on the Web. A...
This paper is a case study on cross-lingual induction of lexical resources for deep, broad-coverage syntactic analysis of German. We use a parallel corpus to induce a classifier f...