Latent semantics in Named Entity Recognition
Expert Systems with Applications (2015)
Abstract
Abstract In this paper, we propose new features for Named Entity Recognition (NER) based on latent semantics. Furthermore, we explore the effect of unsupervised morphological information on these methods and on the {NER} system in general. The newly created {NER} system is fully language-independent thanks to the unsupervised nature of the proposed features. We evaluate the system on English, Spanish, Dutch and Czech corpora and study the difference between weakly and highly inflectional languages. Our system achieves the same or even better results than state-of-the-art language dependent systems. The proposed features proved to be very useful and are the main reason of our promising results.
Authors
BibTex
@article{Konkol20153470, title = "Latent semantics in Named Entity Recognition ", journal = "Expert Systems with Applications ", volume = "42", number = "7", pages = "3470 - 3479", year = "2015", note = "", issn = "0957-4174", doi = "http://dx.doi.org/10.1016/j.eswa.2014.12.015", url = "http://www.sciencedirect.com/science/article/pii/S0957417414007933", author = "Michal Konkol and Tom\'{a}\v{s} Brychc\'{i}n and Miloslav Konop\'{í}k", keywords = "Latent Dirichlet allocation ", abstract = "Abstract In this paper, we propose new features for Named Entity Recognition (NER) based on latent semantics. Furthermore, we explore the effect of unsupervised morphological information on these methods and on the \{NER\} system in general. The newly created \{NER\} system is fully language-independent thanks to the unsupervised nature of the proposed features. We evaluate the system on English, Spanish, Dutch and Czech corpora and study the difference between weakly and highly inflectional languages. Our system achieves the same or even better results than state-of-the-art language dependent systems. The proposed features proved to be very useful and are the main reason of our promising results. " }
