Summarizing scientific articles: experiments with relevance and rhetorical status
Computational Linguistics - Summarization
Blind men and elephants: What do citation summaries tell us about a research article?
Journal of the American Society for Information Science and Technology
Identification of Bibliographic Information Written in Both Japanese and English
ECDL '08 Proceedings of the 12th European conference on Research and Advanced Technology for Digital Libraries
Mention detection crossing the language barrier
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Using citations to generate surveys of scientific paradigms
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Towards multi-paper summarization reference information
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
Automatic creation of a technical trend map from research papers and patents
PaIR '10 Proceedings of the 3rd international workshop on Patent information retrieval
| Hi-index | 0.00 |
The history of the elemental technologies (underlying technologies) used in a particular research field is essential for analyzing technical trend in the field. However, it is too costly and time-consuming to collect and read all of the papers in the field for the purpose of this analysis. Therefore, we have constructed a system that can recognize the application of elemental technologies to any research field. We focus on the structure of research papers' titles for the extraction of elemental technologies. In research papers' titles, particular expressions, such as "using" or "is based on", are often used. The terms immediately after these expressions are considered elemental technologies. Therefore, we used these expressions as cue phrases, and extracted elemental technologies from both English and Japanese titles. We conducted experiments to investigate the effectiveness of our method for analyzing the structure of titles. We obtained Recall and Precision scores of 0.825 and 0.816, respectively, for the analysis of Japanese titles, and scores of 0.735 and 0.780, respectively, for English titles. Finally, we constructed a system that creates a technical trend map for a given research field.