Cognitively Inspired Natural Language Processing

Abhijit Mishra is currently a part of IBM Research, Bangalore, India, where he serves as a Research Scientist in the Department of Cognitive Solutions and Services. Prior to joining IBM Research, he was a PhD student at the Department of Computer Science and Engineering, Indian Institute of Technology Bombay. He interned at the Center for Research and Innovation in Translation and Translation Technologies, CBS, Copenhagen under the guidance of Prof. Michael Carl. Abhijit was also a part of “Developing Multilingual Resources for Indian Languages through Crowdsourcing,” a project launched by the IIT Bombay in collaboration with Xerox Research Center India, Bangalore. The aim of the project was to build a system that helps NLP developers customize and float linguistic annotation tasks using popular crowdsourcing service providers (like Amazon’s Mechanical Turk). Abhijit is currently involved in multiple projects based on Natural Language Generation.Prof. Pushpak Bhattacharyya is a recent past President of the ACL (2016–17). He is Director of the IIT Patna and Vijay and Sita Vashee Chair Professor at the Department of Computer Science and Engineering, IIT Bombay. He studied at the IIT Kharagpur (BTech), IIT Kanpur (MTech) and IIT Bombay (PhD) and has been a visiting scholar and faculty at MIT, Stanford, UT Houston and University Joseph Fourier (France). Prof. Bhattacharyya’s main research areas are Natural Language Processing, Machine Learning and AI. He has published more than 250 research papers and led government and industry projects of international and national importance. Author of the textbook ‘Machine Translation,’ he is a Fellow of the National Academy of Engineering, Eminent Engineer awardee of the Institute of Engineers India, and a recipient of the Patwardhan Award (IIT Bombay) and VNMM Award (IIT Roorkee) – both for technology development – and faculty grants from IBM, Microsoft, Yahoo and the United Nations.

• Chapter 1. Introduction.- Chapter 2. Eye-tracking: Theory, Methods, and Applications in Language Processing and Other Areas.- Chapter 3. Estimating Annotation Complexities of Text Using Gaze and Textual Information - Case studies of Translation and Sentiment Annotation.- Chapter 4. Scanpath Complexity: Combining Gaze Attributes for Modeling Effort in Text Reading/Annotation.- Chapter 5. Predicting Readers’ Sarcasm Understandability by Modeling Gaze Behavior.- Chapter 6. Harnessing Cognitive Features for Sentiment Analysis and Sarcasm Detection.- Chapter 7. Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network.- Chapter 8. Conclusion and Future Directions.