By Manoj K. Sachan, Gurpreet Singh Lehal, Vijender Kumar Jain (auth.), Chandan Singh, Gurpreet Singh Lehal, Jyotsna Sengupta, Dharam Veer Sharma, Vishal Goyal (eds.)
This publication constitutes the refereed court cases of the foreign convention on details platforms for Indian Languages, ICISIL 2011, held in Patiala, India, in March 2011. The sixty three revised papers provided have been rigorously reviewed and chosen from 126 paper submissions (full papers in addition to poster papers) and 25 demo submissions. The papers tackle all present features on localization, e-governance, web pages accessibility, seek engine and knowledge retrieval platforms, on-line and offline OCR, handwriting popularity, desktop translation and transliteration, and text-to-speech and speech popularity - all with a specific specialise in Indic scripts and languages.
Read or Download Information Systems for Indian Languages: International Conference, ICISIL 2011, Patiala, India, March 9-11, 2011. Proceedings PDF
Similar international books
The Routledge International Handbook of Globalization Studies (Routledge International Handbooks)
The Routledge International Handbook of Globalization reports deals scholars transparent and proficient chapters at the historical past of globalization and key theories that experience thought of the explanations and outcomes of the globalization procedure. There are substantial sections taking a look at demographic, monetary, technological, social and cultural alterations in globalization.
This quantity attests to the energy of differential geometry because it probes deeper into its inner constitution and explores ever widening connections with different topics in arithmetic and physics. To such a lot folks Professor S. S. Chern is glossy differential geometry, and we, his scholars, are thankful to him for best us to this fertile panorama.
This publication constitutes the completely refereed revised chosen papers from the second one IAPR foreign Workshop, PSL 2013, held in Nanjing, China, in may well 2013. the ten papers integrated during this quantity have been conscientiously reviewed and chosen from 26 submissions. partly supervised studying is a swiftly evolving quarter of computing device studying.
Additional resources for Information Systems for Indian Languages: International Conference, ICISIL 2011, Patiala, India, March 9-11, 2011. Proceedings
Sample text
The contextual window of the size seven, prefix and suffix length and NE information of the previous word, current word and different digit features have been used. 45% respectively for the current NER Hindi system has been found. The performance of the system can further be improved by using the Part-OfSpeech (POS) information of the current and surrounding words also. References 1. : A Hybrid Approach for Named Entity Recognition in Indian Languages. In: Proceedings of the IJCNLP 2008 Workshop on NER for South and South East Asian Languages, Hyderabad, India, pp.
From each of 41 test documents, we extract the desired number of keyphrases using the proposed method (discussed in section 3) and the baseline method (discussed in section 4). The number of keyphrases to be extracted from a document is set to 5, 10 and 15. We have evaluated the proposed keyphrase extraction system using the well known metrics: precision and recall. The precision and recall are defined as follows: Precision = N N and Recall = M K Where, N = number of keyphrases matched, K = number of keyphrases generated by the system and M = number of keyphrases generated manually.
Keywords: Segmentation, half character, over segmentation. 1 Introduction The simplest technique to segment the characters is to use inter-character gap between the characters. This technique cannot be applied on touching half characters. Also, the technique used to segment the printed characters cannot be applied to handwritten documents due to different writing styles, different sizes of characters and different shapes of characters in texts written by different people. The presence of half characters in handwritten text makes the problem of segmentation more complex.
