CRF-based Czech Named Entity Recognizer and Consolidation of Czech NER Research
Text, Speech and Dialogue (2013)
Research topics:
Named Entity RecognitionAbstract
In this paper, we present our effort to consolidate and push further the named entity recognition (NER) research for the Czech language. The research in Czech is based upon a non-standard basis. Some systems are constructed to provide hierarchical outputs whereas the rests give flat entities. Direct comparison among these system is therefore impossible. Our first goal is to tackle this issue. We build our own NER system based upon conditional random fields (CRF) model. It is constructed to output either flat or hierarchical named entities thus enabling an evaluation with all the known systems for Czech language. We show a 3.5 – 11% absolute performance increase when compared to previously published results. As a last step we put our system in the context of the research for other languages. We show results for English, Spanish and Dutch corpora. We can conclude that our system provides solid results when compared to the foreign state of the art.
Authors
BibTex
@inproceedings{Konkol:2013, year = {2013}, booktitle = {Text, Speech and Dialogue}, volume = {8082}, series = {Lecture Notes in Computer Science}, editor = {Habernal, Ivan and Matou\v{s}ek, V\'{a}clav}, title = {CRF-based Czech Named Entity Recognizer and Consolidation of Czech NER Research}, publisher = {Springer Berlin Heidelberg}, keywords = {Named Entity Recognition, Conditional Random Fields, Czech Named Entity Corpus}, author = {Konkol, Michal and Konop\'{i}k, Miloslav}, pages = {153-160}, abstract = {In this paper, we present our effort to consolidate and push further the named entity recognition (NER) research for the Czech language. The research in Czech is based upon a non-standard basis. Some systems are constructed to provide hierarchical outputs whereas the rests give flat entities. Direct comparison among these system is therefore impossible. Our first goal is to tackle this issue. We build our own NER system based upon conditional random fields (CRF) model. It is constructed to output either flat or hierarchical named entities thus enabling an evaluation with all the known systems for Czech language. We show a 3.5 -- 11\% absolute performance increase when compared to previously published results. As a last step we put our system in the context of the research for other languages. We show results for English, Spanish and Dutch corpora. We can conclude that our system provides solid results when compared to the foreign state of the art.} }
