Summarizing scientific articles: experiments with relevance and rhetorical status
Computational Linguistics - Summarization
Extraction of regulatory gene/protein networks from Medline
Bioinformatics
The BioScope corpus: annotation for negation, uncertainty and their scope in biomedical texts
BioNLP '08 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
Identifying the epistemic value of discourse segments in biology texts
IWCS-8 '09 Proceedings of the Eighth International Conference on Computational Semantics
Automatic annotation of speculation in biomedical texts: new perspectives and large-scale evaluation
NeSp-NLP '10 Proceedings of the Workshop on Negation and Speculation in Natural Language Processing
Hi-index | 0.00 |
Biological papers contain a huge amount of results and ideas that are difficult to manage. Researchers are not only interested in finding relevant information but they also need to know how the authors of papers get the results. Thus, it is interesting to identify the methods used and to distinguish for example between speculations, observations and deductions. Biologists need also to distinguish between new and prior information, especially to identify the real new output of a study. In order to respond to these needs, we propose a linguistic model based on the discursive categories. This model aims to develop the BioExcom tool for the automatic production of thematic sheets using the Contextual Exploration processing. BioExcom is already able to detect speculative sentences and to categorize them into new and prior speculation. The other categories of the model will be developed using the proposed linguistic markers.