Current Research Topics (2014)

Tadayoshi Hara

Research Topic (Tadayoshi Hara)
Parsing Technologies: The technologies for analyzing syntactic and semantic structures of natural language sentences. Current main research topics are mainly the following two:
– To achieve flexible and robust parsing technologies for real-world texts with various styles and representations.
– To reconsider and refine parsing technologies based on feedback from observation of human reading behavior, mainly on human eye-movements.

Pontus Stenetorp

Research Topic (Pontus Stenetorp)
Main interests in Information Extraction (IE), semantic representations and the evaluation of NLP methods.

Pascual Martinez Gomez

Research Topic (Pascual Martinez Gomez)

Eye-tracking devices find applications in human-machine interaction, hypothesis testing in psycholinguistic and usability studies, relevant feature extraction when designing models related to human behavior and to build user-centered information systems. I aim at providing a general and robust framework to do quantitative analysis and inference using data collected by eye-trackers when users read text. To achieve this objective, first the accuracy of eye-trackers has to be increased beyond sensor capabilities by using information from the content or the structure of the text. Then, natural language processing techniques have to be used to process text appearing on the screen and the recognized reading word sequence. Within this framework, it will be possible to better understand user’s intentions, record knowledge acquisition and predict information needs. The intention is to build a user model and user model of the World from texts that users have read. This opens the door to more personalized systems with on-line adaptation capabilities.

Minh-Quoc NGHIEM

Research Topic (Minh-Quoc NGHIEM)
The final purpose of my research is to extract the relation between mathematical expressions and find out which mathematical expressions tend to be used in a typical situation. For example, the Euclidean distance and Mahalanobis distance are usually used in clustering problem.

Currently I am working on interpreting the meaning of mathematical expressions and exploring the use of MathML Parallel Markup Corpora for automatic understanding of mathematical expressions, the task of which is formulated as a translation from Presentation to Content MathML Markups.