Most of the work on treebank-based statistical parsing exclusively uses the WallStreet-Journal part of the Penn treebank for evaluation purposes. Due to the presence of this quasi...
General information retrieval systems are designed to serve all users without considering individual needs. In this paper, we propose a novel approach to personalized search. It c...
Yuanhua Lv, Le Sun, Junlin Zhang, Jian-Yun Nie, Wa...
This paper presents a new approach based on Equivalent Pseudowords (EPs) to tackle Word Sense Disambiguation (WSD) in Chinese language. EPs are particular artificial ambiguous wor...
An open-domain spoken dialog system has to deal with the challenge of lacking lexical as well as conceptual knowledge. As the real world is constantly changing, it is not possible...
The LOGON MT demonstrator assembles independently valuable general-purpose NLP components into a machine translation pipeline that capitalizes on output quality. The demonstrator ...
We discuss Image Sense Discrimination (ISD), and apply a method based on spectral clustering, using multimodal features from the image and text of the embedding web page. We evalu...
Nicolas Loeff, Cecilia Ovesdotter Alm, David A. Fo...
Statistical parsers trained and tested on the Penn Wall Street Journal (WSJ) treebank have shown vast improvements over the last 10 years. Much of this improvement, however, is ba...
We present a novel translation model based on tree-to-string alignment template (TAT) which describes the alignment between a source parse tree and a target string. A TAT is capab...
The interpretation of temporal expressions in text is an important constituent task for many practical natural language processing tasks, including question-answering, information...
A number of metrics for automatic evaluation of machine translation have been proposed in recent years, with some metrics focusing on measuring the adequacy of MT output, and othe...