In this paper, we propose a novel approach of image annotation by constructing a hierarchical mapping between lowlevel visual features and text features utilizing the relations wi...
We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach i...
This paper proposes an approach to enhance dependency parsing in a language by using a translated treebank from another language. A simple statistical machine translation method, ...
We propose a new approach to characterizing the timeline of a text: temporal dependency structures, where all the events of a narrative are linked via partial ordering relations l...
Oleksandr Kolomiyets, Steven Bethard, Marie-Franci...
The main purpose of communication is to exchange information. Any discourse understanding model should be able to process the flow of information throughout the entire text. Accor...