Summary of the paper
| Title | Improving Domain-specific Entity Recognition with Automatic Term Recognition and Feature Extraction |
|---|---|
| Authors | Ziqi Zhang, José Iria and Fabio Ciravegna |
| Abstract | Domain specific entity recognition often relies on domain-specific knowledge toimprove system performance. However, such knowledge often suffers from limiteddomain portability and is expensive to build and maintain. Therefore, obtainingit in a generic and unsupervised manner would be a desirable feature fordomain-specific entity recognition systems. In this paper, we introduce anapproach that exploits domain-specificity of words as a form ofdomain-knowledge for entity-recognition tasks. Compared to prior work in thefield, our approach is generic and completely unsupervised. We empirically showan improvement in entity extraction accuracy when features derived by ourunsupervised method are used, with respect to baseline methods that do notemploy domain knowledge. We also compared the results against those of existingsystems that use manually crafted domain knowledge, and found them to becompetitive. |
| Language | Statistical and machine learning methods |
| Topics | Named Entity recognition, Information Extraction, Information Retrieval, Statistical and machine learning methods |
Full paper  |
Improving Domain-specific Entity Recognition with Automatic Term Recognition and Feature Extraction |
| Bibtex | @InProceedings{ZHANG10.214, author = {Ziqi Zhang, José Iria and Fabio Ciravegna}, title = {Improving Domain-specific Entity Recognition with Automatic Term Recognition and Feature Extraction}, 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} } |