Pure statistical parsing systems achieves high in-domain accuracy but performs poorly out-domain. In this paper, we propose two different approaches to produce syntactic dependenc...
Background: Prediction of protein structural classes (a, b, a + b and a/b) from amino acid sequences is of great importance, as it is beneficial to study protein function, regulat...
This paper presents some preliminary results of our dependency parser for Thai. It is part of an ongoing project in developing a syntactically annotated Thai corpus. The parser ha...
Abstract. We propose an independence criterion based on the eigenspectrum of covariance operators in reproducing kernel Hilbert spaces (RKHSs), consisting of an empirical estimate ...
Arthur Gretton, Olivier Bousquet, Alex J. Smola, B...
This paper presents a new technique, called Symbolic Program Decomposition (or SPD), for symbolic execution of multiple paths that is more scalable than existing techniques, which...