We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...
The goal of this project is to develop solutions to enhance interoperability between bioinformatics applications. Most existing applications adopt different data formats, forcing ...
Juan Raymundo Iglesias, Gopal Gupta, Enrico Pontel...
Recently the LATL has undertaken the development of a multilingual translation system based on a symbolic parsing technology and on a transfer-based translation model. A crucial c...
Several methods are known for parsing languages generated by Tree Adjoining Grammars (TAGs) in O(n 6) worst case running time. In this paper we investigate which restrictions on T...
This paper presents a novel technique called "universal guides" which explores inherent properties of logic grammars (changing variable binding status) in order to chara...