论文信息 - Rule Based Hindi Part of Speech Tagger

Rule Based Hindi Part of Speech Tagger

Part of Speech Tagger is an important tool that is used to develop language translator and information extraction. The problem of tagging in natural language processing is to find a way to tag every word in a sentence. In this paper, we present a Rule Based Part of Speech Tagger for Hindi. Our System is evaluated over a corpus of 26,149 words with 30 different standard part of speech tags for Hindi. The evaluation of the system is done on the different domains of Hindi Corpus. These domains include news, essay, and short stories. Our system achieved the accuracy of 87.55%.

[1] Selvadoss Thanamani Dr.Antony. Parts Of Speech Tagging for Indian Languages: A Literature Survey , 2011 .

[2] Anirudh Mani,et al. Part of Speech Tagging and Chunking with Conditional Random Fields , 2022 .

[3] Balaraman Ravindran,et al. Part Of Speech Tagging and Chunking with HMM and CRF , 2006 .

[4] Pushpak Bhattacharyya,et al. Morphological Richness Offsets Resource Demand - Experiences in Constructing a POS Tagger for Hindi , 2006, ACL.

[5] Amit Mishra,et al. Part of Speech Tagging for Hindi Corpus , 2011, 2011 International Conference on Communication Systems and Network Technologies.

[6] Eric Brill,et al. A Simple Rule-Based Part of Speech Tagger , 1992, HLT.

[7] Pushpak Bhattacharyya,et al. Hindi POS Tagger Using Naive Stemming : Harnessing Morphological Information Without Extensive Linguistic Knowledge , 2008 .

[8] ABOUT IIT BOMBAY & , 2022 .

[9] Gurpreet Singh Josan,et al. Part of Speech Taggers for Morphologically Rich Indian Languages: A Survey , 2010 .

[10] Shachi Mall,et al. Hindi Part of Speech Tagging and Translation , 2011 .

[11] Gurpreet Singh Lehal,et al. Using Hidden Markov Model to improve the accuracy of Punjabi POS tagger , 2011, 2011 IEEE International Conference on Computer Science and Automation Engineering.