Sambhav Jain

A Two-Stage Approach for Computing Associative Responses to a Set of Stimulus Words

This paper describes the system submitted by the IIIT-H team for the CogALex-2014 shared task on multiword association. The task involves generating a ranked list of responses to a set of stimulus words. The two-stage approach combines the strength of neural network based word embeddings and frequency based association measures. The system achieves an accuracy of 34.9% over the test set.

Effect of transliteration on readability

We present our efforts on studying the effect of transliteration, on the human readability. We have tried to explore the effect by studying the changes in the eye-gaze patterns, which are recorded with an eye-tracker during experimentation. We have chosen Hindi and English languages, written in Devanagari and Latin scripts respectively. The participants of the experiments are subjected to transliterated words and asked to speak the word. During this, their eye movements are recorded. The eye-tracking data is later analyzed for eye-fixation trends. Quantitative analysis of fixation count and duration as well as visit count is performed over the areas of interest.