Browsing by Author "Dias, GV"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • Thumbnail Image
    item: Conference-Full-text
    Ananya - a named-entity-recognition (ner) system for sinhala language
    (IEEE, 2016-04) Manamini, SAPM; Ahamed, AF; Rajapakshe, RAEC; Reemal, GHA; Jayasena, S; Dias, GV; Ranathunga, S; Jayasekara, AGBP; Bandara, HMND; Amarasinghe, YWR
    Named-Entity-Recognition (NER) is one of the major tasks under Natural Language Processing, which is widely used in the fields of Computer Science and Computational Linguistics. However, the amount of prior research done on NER for Sinhala is very minimal. In this paper, we present data-driven techniques to detect Named Entities in Sinhala text, with the use of Conditional Random Fields (CRF) and Maximum Entropy (ME) statistical modeling methods. Results obtained from experiments indicate that CRF, which provided the highest accuracy for the same task for other languages outperforms ME in Sinhala NER as well. Furthermore, we identify different linguistic features such as orthographic word level and contextual information that are effective with both CRF and ME Algorithms.
  • Thumbnail Image
    item: Conference-Full-text
    HTML5 Based Email Client with Touch Enabled Advanced User Interface for Tabs and Tablets
    Madhuka, GPD; Dias, GV
    The Internet has become as a very powerful platform that has changed the way we do business and the way we communicate. E-Mail is an essential tool for both cooperative world and individuals for communicating. Web-based e-mail systems have become more popular among the internet users with time. Internet and the devices that we use to access the internet are rapidly changing time to time. Among the recent evolutions the most significant of them is HTML5 incorporated mobile technology with hi-tech devices like tabs, iPads and tablets with touch sensitivity. However, the major problem occurs when different levels of resolutions arisewithmodern devices. Some devices support touch, multi-touch, gestures, keyboards and stylus. User-interface of email web clients hasnt improved in the way hi-tech devices evolved. Handling different types of interactions depends on the device and way that user handles it. We have developed HTML5 off-line supporting web-based UI for e-mail system to overcome this issue and to provide a highly user based interactive, responsive and efficient process even in slow network connections. Our approach is based on HTML5 features and client side on java-scripting. Our system is capable of running on a browser without installing any plug-ins. Depending on the device resolution and user interaction (one finger touch/ both hands or external keyboard) email client has provisions to transform the web UI to give better interaction for the user and email system.
  • Thumbnail Image
    item: Thesis-Abstract
    Sinhala T9 text entry system
    Dewapura, MH; Dias, GV
    T9 Text Input is an input technology used in mobile devices. It lets words be formed by a single key press for each letter, as opposed to the multiple key press approach used in the older generation of mobile phones. It works via active reference to a dictionary of commonly used words. T9 databases are currently available in 15 different character scripts in 62 languages including specialized language engines for Alphabetic, Chinese and Japanese languages. However it is not available for Sinhala. Development of T9 is more valuable for Sinhala than English as the number of letters assigned to a key in the Sinhala keypad is more than that of the English keypad./ We developed a system for predictive keypad text entry in Sinhala. Predictive keypad text entry allows the user to type words efficiently just pressing a key one time for each letter./ The major objectives achieved in this project are the building of a Sinhala word database, identification of common words and development of the algorithm for predictive keypad text entry and an application for the T9 PC simulator. We used the Sinhala keypad layout used in the Nokia mobile phones for our project./ A large number of Sinhala words were collected, several tools to process the words were developed and a database, mapping key sequences to prioritized lists of Sinhala words, was built. A PC application to simulate keypad text entry, update the database with new words and to change word priorities was developed./ Finally we compared the required number of key presses for Sinhala text input using T9 and using multi-tap text entry, and showed that our system enables users to enter Sinhala text easily, quickly and efficiently.