Cognive NLP research at the Centre for Indian Language Technology (CFILT), aempts to gain insights into the cognive underpinnings of human language processing and understanding. The insights are then translated to methods and models that contribute to the field of NLP by achieving the following objecves: (i) Opmising Human Annotaon Effort for beer annotaon management, and (2) Improving exisng NLP systems by introducing cognive features. Today's NLP is highly stascal in nature and needs massive amount of human annotated data. In a typical cognive NLP seng, apart from collecng the annotaons, we aim to record annotators' acvies in the form of their eye movement paerns, key-strokes and neuro-electric signals obtained using EEG. Through a series of studies using eye-tracking alone, we show that data of such kind, can be used to model complexies of tasks like translaon and senment annotaon, where eye-movement data is used to train classifiers that model annotaon effort for the specified tasks. This can be useful for beer annotaon management (for example, proposing beer annotaon cost models in a crowd-sourcing scenario). This research also showed that eye movement data can be used to extract cognion-driven Features, to be used for difficult NLP tasks like Senment Analysis and Sarcasm Detecon. The proposed approaches consistently perform beer than state- of-the-art senment and sarcasm classifiers, showing that cognive features can be useful for tasks that are nuanced by linguisc subtlees. The Cognive NLP group at CFILT has collaborated with Copenhagen Business School, Copenhagen, and IBM Research Lab, Delhi, on several projects. The Cognive Lab at CFILT is equipped with a high-end SR Research Eye-link 1000 Plus Eye-tracker for experimentaon. COGNITIVE NLP Prof. Pushpak Bhaacharyya, Department of Computer Science and Engineering, [email protected]