ABSTRACT
We were asked to evaluate input mechanisms for touch-screen devices with the objective of standardising one of them for each of 14 major languages of India. For this purpose, we propose a protocol that consists of a 45-minute long training session, a 20-word first-time usability test, and a longitudinal test consisting of about 30 sessions, each of which required the user to type about 10 phrases 4 to 6 words long (a total of 300 phrases). The evaluation should be done with school children from standards 4th to 7th. The course of the evaluation may last 2-4 weeks for each user. To help follow the protocol over this long period and to collate the data, we offer a tool. Currently, we provide test corpora for Assamese, Bengali, Gujarati, Hindi, Kannada, Marathi, Odia, Tamil, Telugu, and Urdu. We have ensured that each corpus represents a mix of informal communication between people, popular phrases from films, songs, poetry and public discourse, and formal texts from school books and literature. We have tagged each phrase according to typing difficulty, phrase length, and memorability and age appropriateness. We evaluated the protocol through pilot tests with 206 users in Marathi, Gujarati, Hindi, Bengali, Odia, Assamese and Tamil. In this paper, we present the original protocol, the detailed findings from the Marathi pilots, and the proposed modifications to the protocol.
- Census 2001, http://en.wikipedia.org/wiki/List_of_languages_by_number_of_native_speakers_in_IndiaGoogle Scholar
- Jung, Y., Joshi, D., Narayanan-Saroja, V., and Desai, D. P. 2011. Solving the great Indian text input puzzle: touch screen-based mobile text input design. In Proceedings of the 13th International Conference on Human Computer Interaction with Mobile Devices and Services (Stockholm (2011) MobileHCI '11, ACM, New York, NY 313--322. DOI= http://dl.acm.org/citation.cfm?id=2037421 Google ScholarDigital Library
- FIRSTPOST, http://www.firstpost.com/business/biztech/3g-boom-afoot-in-india-to-cover-90-of-a-grade-circles-by-2015-1618115.htmlGoogle Scholar
- Joshi, A., Ganu, A., Chand, A., Parmar, V., and Mathur, G. 2004. Keylekh: a keyboard for text entry in Indic scripts. In CHI'04 extended abstracts on Human factors in computing systems, (Vienna 2004) CHI EA '04. ACM, New York, NY, 928--942. DOI= http://dl.acm.org/citation.cfm?id=985950 Google ScholarDigital Library
- Rathod, A. and Joshi, A.2002. A Dynamic Text Input scheme for phonetic scripts like Devanagari. 2002. In Proceedings of Development by Design. (Bangalore 2002)Google Scholar
- Mistry, P. and Nayak, N. 2007. AKSHAR: A mechanism for inputting Indic scripts on digital devices, (Hyderabad 2007) 18--20. USID,Google Scholar
- Ghosh, S. and Joshi, A. 2014. Text Entry in Indian Languages on Mobile: User Perspectives. In Proceedings of the India HCI 2014 Conference on Human Computer Interaction. (Delhi 2014) IndiaHCI '14. ACM, New York, NY, 55--63. DOI= http://dl.acm.org/citation.cfm?id=2676710 Google ScholarDigital Library
- Hind Keyboards, https://play.google.com/store/search?q=Hindi+keyboard&c=appsGoogle Scholar
- Joshi, M., Joshi, A. N., Emmadi, N., and Malsattar, N. 2014. Swarachakra keyboard for Indic scripts. In Proceedings of the 1st International Conference on Mobile Software Engineering and Systems, (Hyderabad 2014) MOBILESoft 2014. ACM, New York, NY, 5--6. DOI= http://dl.acm.org/citation.cfm?id=2593905 Google ScholarDigital Library
- Sharma, M. K. 2013. Word Prediction System with Virtual Keyboard for Text Entry in Hindi. In ACM Transactions on Asian Language Information Processing, (ACM 2013) ACM, New York, NY, Article No. 8. DOI= http://dl.acm.org/citation.cfm?id=2617590 Google ScholarDigital Library
- Hinkle, L., Brouillette, A., Jayakar, S., Gathings, L., Lezcano, and M., Kalita, J. 2013. Design and Evaluation of Soft Keyboards for Brahmic Scripts. In ACM Transactions on Asian Language Information Processing. (ACM 2013) ACM New York, NY, Article No. 6. DOI= http://dl.acm.org/citation.cfm?id=2461318 Google ScholarDigital Library
- Malsattar, N., Emmadi, N., and Joshi, M.2014. Testing the efficacy of an Indic script virtual keyboard: Swarachakra. In: Proceedings of the India HCI 2014 Conference on Human Computer Interaction, (Delhi 2014). IndiaHCI '14. ACM New York, 160--165. DOI= http://dl.acm.org/citation.cfm?id=2677203 Google ScholarDigital Library
- TDIL: Inscript Standard, http://www.tdil-dc.in/index.php?option=com_vertical&parentid=12Google Scholar
- MacKenzie, I. S. and Soukoreff, R. W. 2003. Phrase sets for evaluating text entry techniques. In: CHI'03 extended abstracts on Human factors in computing systems,(Florida 2003) CHI EA '03. ACM New York, 754--755. DOI= http://dl.acm.org/citation.cfm?id=765971 Google ScholarDigital Library
- Joshi, A., Dalvi, G., Joshi, M., Rashinkar, P., and Sarangdhar, A. 2011. Design and evaluation of Devanagari virtual keyboards for touch screen mobile phones. In Proceedings of the 13th In-ternational Conference on Human Computer Interaction with Mobile Devices and Services. (Stockholm 2011) MobileHCI'11. ACM New York, 323--332.DOI= http://dl.acm.org/citation.cfm?id=2037422 Google ScholarDigital Library
- Mitra, S.2003. Minimally invasive education: a progress report on the "hole-in-the-wall" experiments. In British Journal of Educational Technology, (2003) vol. 34, 367--371. DOI=http://onlinelibrary.wiley.com/doi/10.1111/1467-8535.00333/abstractGoogle ScholarCross Ref
- CDAC Inscript: Unified Virtual Keyboard for Indian Languages, http://www.cdac.in/index.aspx?id=dl_android_uvkilGoogle Scholar
- Swarachakra Marathi Keyboard, https://play.google.com/store/apps/details?id=iit.android.swarachakraMarathiGoogle Scholar
- Google Hindi input, https://play.google.com/store/apps/details?id=com.google.android.apps.inputmethod.hindiGoogle Scholar
- Angry Birds, https://play.google.com/store/apps/details?id=com.rovio.angrybirdsGoogle Scholar
- Census 2001, http://en.wikipedia.org/wiki/List_of_countries_by_number_of_Internet_usersGoogle Scholar
- Joshi, A., Dalvi, G., and Joshi, M. 2014. Corpus of Marathi Word Frequencies from Touch-Screen Devices Using Swarachakra Android Keyboard. In: Proceedings of the India HCI 2014 Conference on Human Computer Interaction, p. 74. ACM, Delhi (2014) Google ScholarDigital Library
- FIRE: Forum for Information Retrieval (FIRE), Information Retrieval Society of India. (12 2-4). Mumbai, Maharashtra, India, http://www.isical.ac.in/~fire/2011/index.html, 2011Google Scholar
- Baker, P., Hardie, A., McEnery, T., Xiao, R., Bontcheva, K., Cunningham, H., Gaizauskas, R., Hamza, O., Maynard, D., Tablan, V., Ursu, C., and Leisher, M. 2004. Corpus linguistics and South Asian languages: Corpus creation and tool development. Literary and Linguistic Computing, vol. 19, pp. 509--524. (2004)Google ScholarCross Ref
- Walmsley, W. S., Snelgrove, and W. X., Truong, K. N. 2014. Disambiguation of imprecise input with one-dimensional rotational text entry. ACM Transactions on Computer-Human Interaction, (2014) ACM New York, NY, vol. 21, 4. DOI=http://dl.acm.org/citation.cfm?id=2542544 Google ScholarDigital Library
- Markussen, A., Jakobsen, M. R., and Hornbæk, K. 2014. Vulture: a mid-air word-gesture keyboard. In Proceedings of the 32nd annual ACM conference on Human factors in computing systems, (Toronto 2014) CHI '14, ACM, New York, NY 1073--1082. DOI= http://dl.acm.org/citation.cfm?id=2556964 Google ScholarDigital Library
- Dearman, D., Karlson, A., and Meyers, B., Bederson, B. 2010. Multi-modal text entry and selection on a mobile device. In: Proceedings of Graphics Interface 2010, (Toronto 2010) GI '10, Canadian Information Processing Society Toronto, Ont., Canada, 19--26. DOI=http://dl.acm.org/citation.cfm?id=1839219 Google ScholarDigital Library
- ASER, http://img.asercentre.org/docs/Publications/ASER%20Reports/ASER%202014/fullaser2014 mainreport.pdfGoogle Scholar
- Jones, E., Alexander, J., Andreou, A., Irani, P., and Subramanian, S. 2010. GesText: accelerometer-based gestural text-entry systems. In Proceedings of the SIGCHI Conference on Human Fac-tors in Computing Systems,(Atlanta 2010) CHI'10, ACM New York, NY, 2173--2182. DOI= http://dl.acm.org/citation.cfm?id=1753655 Google ScholarDigital Library
- Fuccella, V., Isokoski, P., and Martin, B. 2013. Gestures and widgets: performance in text editing on multi-touch capable mobile devices. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, (Paris 2013) CHI '13, ACM New York, NY, 2785--2794. DOI= http://dl.acm.org/citation.cfm?id=2481385 Google ScholarDigital Library
- Jain, M., Tekchandani, and K., Truong, K. N. 2013. Evaluating the Effect of Phrase Set in Hindi Text Entry. In Human-Computer Interaction--INTERACT 2013, (Heidelberg 2013). Interact-2013 195--202. DOI= http://www.dgp.toronto.edu/~mjain/INTERACT-2013a.pdfGoogle ScholarCross Ref
- Sarcar, S. and Panwar, P. 2013. Eyeboard++: an enhanced eye gaze-based text entry system in Hindi. In Proceedings of the 11th Asia Pacific Conference on Computer Human Interaction, (Bangalore 2013) APCHI '13, ACM New York, NY, 354--363. DOI=http://dl.acm.org/citation.cfm?id=2525304 Google ScholarDigital Library
- Swype Marathi Keyboard, https://play.google.com/store/apps/details?id=com.nuance.swype.dtc&hl=enGoogle Scholar
- VKB App tool and corpus, goo.gl/1TsT5AGoogle Scholar
Recommendations
Approximate String Matching Techniques for Effective CLIR Among Indian Languages
WILF '07: Proceedings of the 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets TheoryCommonly used vocabulary in Indian language documents found on the web contain a number of words that have Sanskrit, Persian or English origin. However, such words may be written in different scripts with slight variations in spelling and morphology. In ...
Cognate Identification to improve Phylogenetic trees for Indian Languages
CODS-COMAD '19: Proceedings of the ACM India Joint International Conference on Data Science and Management of DataCognates are present in multiple variants of the same text across different languages. Computational Phylogenetics uses algorithms and techniques to analyze these variants and infer phylogenetic trees for a hypothesized accurate representation based on ...
Transfer Learning for Scene Text Recognition in Indian Languages
Document Analysis and Recognition – ICDAR 2021 WorkshopsAbstractScene text recognition in low-resource Indian languages is challenging because of complexities like multiple scripts, fonts, text size, and orientations. In this work, we investigate the power of transfer learning for all the layers of deep scene ...
Comments