Automatic Language-Independent Induction of Gazetteer Lists Export

@article{5407, abstract = {Adaptation of existing Information Extraction (IE) systems to new languages and domains is the focus of much current research, but progress is often hindered by the lack of available resources to enable developers to get a new system up and running fast. It has previously been shown that a good set of gazetteer lists can have a vital role here, but creation of lists for a new language or domain can be time-consuming and laborious. In this paper we demonstrate a tool for inducing gazetteer lists from a small set of annotated corpora and creating a baseline IE system. We also describe an extension to this, using bootstrapping techniques in order to generate much larger volumes of noisy training texts. High quality results have been achieved in this way on Hindi, Chinese and Arabic.}, author = {Maynard, Diana and Bontcheva, Kalina and Cunningham, Hamish}, citeulike-article-id = {3275539}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.594}, journal = {In Proceedings of 4th Language Resources and Evaluation Conference (LREC?04}, keywords = {arabic, bootstrapping, chinese, gazetteer, hindi, information-extraction}, pages = {2004}, posted-at = {2008-09-16 20:26:10}, priority = {2}, title = {Automatic Language-Independent Induction of Gazetteer Lists}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.594}, year = {2004} }

TY - JOUR ID - 5407 L3 - citeulike-article-id:3275539 N2 - Adaptation of existing Information Extraction (IE) systems to new languages and domains is the focus of much current research, but progress is often hindered by the lack of available resources to enable developers to get a new system up and running fast. It has previously been shown that a good set of gazetteer lists can have a vital role here, but creation of lists for a new language or domain can be time-consuming and laborious. In this paper we demonstrate a tool for inducing gazetteer lists from a small set of annotated corpora and creating a baseline IE system. We also describe an extension to this, using bootstrapping techniques in order to generate much larger volumes of noisy training texts. High quality results have been achieved in this way on Hindi, Chinese and Arabic. JF - In Proceedings of 4th Language Resources and Evaluation Conference (LREC?04 EP - 2004 TI - Automatic Language-Independent Induction of Gazetteer Lists SP - 2004 KW - arabic KW - bootstrapping KW - chinese KW - gazetteer KW - hindi KW - information-extraction AU - Maynard, Diana AU - Bontcheva, Kalina AU - Cunningham, Hamish PY - 2004/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.594 ER -