Summary of the paper
| Title | Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora |
|---|---|
| Authors | Junko Kubo, Keita Tsuji and Shigeo Sugimoto |
| Abstract | In this paper, we propose a method for automatic term recognition (ATR) whichuses the statistical differences of relative frequencies of terms in targetdomain corpus and elsewhere. Generally, the target terms appear more frequentlyin target domain corpus than in other domain corpora. Utilizing suchcharacteristics will lead to the improvement of extraction performance. Most ofthe ATR methods proposed so far only use the target domain corpus and do nottake such characteristics into account. For the extraction experiment, we usedthe abstracts of a women's studies journal as a target domain corpus and thoseof academic journals of 39 domains as other domain corpora. The women's studiesterms which were used for extraction evaluation were manually identified termsin the abstracts. The extraction performance was analyzed and we found that ourmethod outperformed earlier methods. The previous methods were based onC-value, FLR and methods which were also used with other domain corpora. |
| Language | MultiWord Expressions & Collocations |
| Topics | Corpus (creation, annotation, etc.), Information Extraction, Information Retrieval, MultiWord Expressions & Collocations |
Full paper  |
Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora |
| Bibtex | @InProceedings{KUBO10.347, author = {Junko Kubo, Keita Tsuji and Shigeo Sugimoto}, title = {Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |