Title :
Bengali noun phrase chunking based on conditional random fields
Author :
Sarkar, Kamal ; Gayen, Vivekananda
Author_Institution :
Comput. Sci. & Eng. Dept., Jadavpur Univ., Kolkata, India
Abstract :
Noun phrase (NP) chunking deals with extracting the noun phrases from a sentence. While NP chunking is much simpler than parsing, it is still a challenging task to build an accurate and efficient NP chunker. Noun phrase chunking is an important and useful task in many natural language processing applications. It is studied well for English, however not much work has been done for Bengali. This paper presents a Bengali noun phrase chunking approach based on conditional random fields (CRFs) models. Our developed NP chunker has been tested on the ICON 2013 dataset and achieves an impressive F-score of 95.92.
Keywords :
natural language processing; Bengali noun phrase chunking; CRF; English; F-score; ICON 2013 dataset; NP chunker; conditional random fields; natural language processing applications; Artificial neural networks; Computers; Decoding; Training; Vocabulary; Bengali Language; CRF; Conditional Random Fields; Information Overload Problem; Noun Phrase Chunking;
Conference_Titel :
Business and Information Management (ICBIM), 2014 2nd International Conference on
Conference_Location :
Durgapur
Print_ISBN :
978-1-4799-3263-4
DOI :
10.1109/ICBIM.2014.6970957
