Tirthankar Dasgupta

Prototype machine translation system from text-to-Indian sign language

This paper presents a prototype Text-To-Indian Sign Language (ISL) translation system. The system will help dissemination of information to the deaf people in India. This paper also presents the SL-dictionary tool, which can be used to create bilingual ISL dictionary and can store ISL phonological information.

A speech enabled Indian language text to Braille transliteration system

In this paper we present a speech enabled bidirectional automatic Indian language text to Braille transliteration system. The system allows bridging the communication gap between a visually impaired and a sighted person. The present system can be configured to take Indian language text document as input and based on some transliteration rules, can generate the corresponding Braille output. The system is augmented by an Indian language text-to-speech (TTS) system through which a user can get instantaneous audio feedback from the input text. We further extended the system to support transliteration of Dzongkha1 text to Braille. Finally we present an Audio QWERTY editor which allows a visually impaired person to read and write Indian language texts through a computer.

Architecture of a web browser for visually handicapped people

Internet has brought about an incredible improvement in human access to knowledge and information. However, blind people face difficulties in accessing these text materials. Web browsers for the visually handicapped people in the past have been limited to converting documents to Braille or speech, or extracting text and filtering. However, the human aspects of web surfing for blind people have not been adequately addressed. This paper presents an architecture of an open source, light weight web browser that makes it easy for the visually handicapped people to surf the web. The proposed architecture allows a blind person to navigate any web content through simple speech commands and voice feedback to any keyboard operation. The browser will have an integrated text extraction engine that inspects the content of the page to construct a structured representation. The internal nodes of the structure represent various levels of abstraction of the content. This helps in easy and flexible navigation of the page so as to rapidly home into objects of interest. Finally, the browser is integrated to an automatic Text-To-Speech and Text-To-Braille transliteration engine that outputs the selected text in the form of speech and/or Braille.

Implementation of Unicode Complaint Odia Keyboard and Its Evaluation Using Cognitive Model

Odia is the principal regional language of Odisha and the sixth classical language of India. There are more than 33 million people of Odisha speak Odia in their day to day life. However, standard input methods for typing Odia are not very widespread among Odia users. In this paper we present the design and development of a novel Odia keyboard layout that can be used to type Unicode enabled Odia texts in a standard text editor using any QWERTY keyboard. The keyboard layout is based on Unicode 5.0 standard. We have evaluated the performance of our proposed layout with the existing Odia keyboard layouts. We have done this evaluation using cognitive model. Our primary evaluation shows a significant improvement in reducing time irrespective of keystroke, increasing typing speed, reducing error rates as well as easing of learning. We have designed a typing s/w (Baishakhi key logger) for all Odias to learn Odia typing.

Design and evaluation of Bangla keyboard layouts

Bangla is considered as the fifth most frequent spoken language in the world. However, standard input methods for typing Bangla are not very widespread among Bengali users. In this paper we present the design and development of a novel Bangla phonetic keyboard layout that can be used to type Unicode enabled Bangla texts in a standard text editor using any QWERTY keyboard. The keyboard layout is based on Unicode 5.0 standard. We have evaluated the performance of our proposed layout with the existing Bangla keyboard layouts. Our primary evaluation shows a significant improvement in typing speed, and ease of learning and reduction in error rates.

Design and Development of a Bangla Semantic Lexicon and Semantic Similarity Measure

In this paper, we have proposed a hierarchically organized semantic lexicon in Bangla and also a graph based edgeweighting approach to measure semantic similarity between two Bangla words. We have also developed a graphical user interface to represent the lexical organization. Our proposed lexical structure contains only relations based on semantic association. We have included the frequency of each word over five Bangla corpuses in our lexical structure and also associated more details to words such as, whether the words are mythological or not, whether it can be used as verb or not, in order to use the word as a verb which word should be appended to it etc. As we have earlier discussed, this lexicon can be used in various applications like categorization, semantic web, and natural language processing applications like, document clustering, word sense disambiguation, machine translation, information retrieval, text comprehension and question-answering systems.

How Word Order Affects Sentence Comprehension in Bangla: A Computational Approach to Simple Sentence

Sentence comprehension is an integral and important part of whole text comprehension. It involves complex cognitive actions, as a reader has to work through lexical, syntactic and semantic aspects in order to understand a sentence. One of the vital features of a sentence is word order or surface forms. Different languages have evolved different systems of word orders, which reflect the cognitive structure of the native users of that language. Therefore, word order affects the cognitive load exerted by a sentence as experienced by the reader. Computational modeling approach to quantify the effect of word order on difficulty of sentence understanding can provide a great advantage in study of text readability and its applications. Handful of works has done in English and other languages to address the issue. Bangla, which is the fifth mostly spoken languages in the world and a relatively free word order language, still does not have any computational model to quantify the reading difficulty of a sentence. In this paper, we have developed models to predict the comprehending difficulty of a simple sentence according to its different surface forms in Bangla. In the course of action, we have also established that difficulty measures for English do not hold in Bangla. Our model has been validated against an extensive user survey.

A Joint Source Channel Model for the English to Bengali Back Transliteration

In this paper we present an English-to-Bengali back transliteration system that can be used to transliterate Bengali texts written in Romanized English, back to its original script. Our proposed system uses a bilingual parallel corpus of English-Bengali transliterated word pairs and applies both the orthographic as well as phonetic information to two different computational models namely, the joint source channel model and the trigram model, to automatically identify, extract and learning of transliteration unit (TU) pairs from both the source and target language words. Finally, the system predicts the top 10 best possible outcome of the given input text. We further extend our work to make the target word prediction module more robust. This is done by the phonological analysis of the generated target sentence. Both the models have been evaluated with a set of 2000 Romanized Bengali test words. Our initial evaluation results clearly shows that the joint source channel model performs much better than the trigram model.

VoiceMail architecture in desktop and mobile devices for the Blind people

The advancement in computer based accessible systems has opened up many avenues for the visually impaired across a wide majority of the globe. Audio feedback based virtual environment like, the screen readers have helped Blind people to access internet applications immensely. However, a large section of visually impaired people in different countries in particular, the Indian sub-continent could not benefit much from such systems. This was primarily due to the difference in the technology required for Indian languages compared to those corresponding to other popular languages of the world. In this paper, we describe the VoiceMail system architecture that can be used by a Blind person to access e-Mails easily and efficiently. The contribution made by this research has enabled the Blind people to send and receive voice based e-Mail messages in their native language with the help of a computer or a mobile device. Our proposed system GUI has been evaluated against the GUI of a traditional mail server. We found that our proposed architecture performs much better than that of the existing GUIs.

Exploring Linguistic and Graph Based Features for the Automatic Classification and Extraction of Adverse Drug Effects

Adverse drug effects (ADEs) are known to be one of the leading causes of post-therapeutic death. Thus, their identification constitutes an important challenge as the effects of ADEs are often underreported. However, the recent popularity of different social media sources has make it a promising source for ADE extraction. In this paper, we have explored different linguistic and graph topological features to automatically classify short sentences or tweets into ADEs or Non-ADEs. We have further represented the ADE knowledge base into an bipartite network structure of drugs and their side effects to model drug-side effect relationships. The proposed model can also be used to discover implicit ADEs that are not represented in the source data. We have evaluated our proposed models with two openly available ADE dataset. Our evaluation results shows that the proposed model have surpasses the performance of the existing baseline systems.