We present a K-out-of-L voting scheme, i.e., a voting scheme that allows every voter to vote for (up to) K candidates from a set of L candidates. The scheme is receipt-free, which ...
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...
This paper improves the use of pseudowords as an evaluation framework for selectional preferences. While pseudowords originally evaluated word sense disambiguation, they are now c...
In this paper, we propose a novel approach to automatic generation of summary templates from given collections of summary articles. This kind of summary templates can be useful in...
This paper proposes a convolution forest kernel to effectively explore rich structured features embedded in a packed parse forest. As opposed to the convolution tree kernel, the p...