Prashanth V
Contact:
pralav [AT] media [DOT] mit [DOT] edu
lavanya [DOT] prashanth [AT] gmail [DOT] com
Hi வணக்கம் ! I am a PhD student at MIT Media lab where I work in the Laboratory of Social Machines group with Deb Roy. I enjoy exploring novel approaches to tackle real-world problems through the lens of AI (deep learning, natural language processing & computer vision). I'm interested in developing and applying different learning methods to data (including multi-modal data) from different domains such as social media, news, personal and non-fictional narratives, movie dialogues, etc.
Recently, my research is focused on two broad themes: (a) uncovering latent semantic information from natural language for text understanding and generation, and (b) enabling AI systems to develop social intelligence i.e. learning to empower AI systems to better model, understand and reason about human behaviour (persona modeling, mental state representation, common sense reasoning, theory of mind).
Lifelong Social Event Representation
Model Motives & Emotions from Personal Narratives
DAPPER: Domain-adapted Persona Representation
Generating Aversarial Examples for Text Classifiers
Detecting Hate Speech
Learning Personas from Dialogue
Video SemNet: Memory-Augmented Network
Content Consistent Style Transfer
Tweet2vec: Learning Tweet Embeddings
Deep Multi-modal Multi-task Learning
DeepSpace: Mood-based Texture Generation
Auris:Creating Affective Virtual Spaces from Music
Identification of Representative Content on Twitter
Categorization of Election-related Tweets
TweetVista: AI Tool for Exploring conversations
Handwritten Tamil Recognition
- Vijayaraghavan, Prashanth and Deb Roy. "Learning to Model Narrative Structure Using Protagonist’s Motives & Emotions.", (Under review)
- Vijayaraghavan, Prashanth and Deb Roy. "Learning to Model Human Motives and Emotions from Personal Narratives Using External Knowledge And Entity Tracking." To Appear in Proceedings of the Web Conference 2021. 2021.
- Vijayaraghavan, Prashanth and Deb Roy. "Lifelong Social Event Representation Learning." To Appear in Proceedings of the 16th conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2021.
- Vijayaraghavan, Prashanth, Eric Chu, and Deb Roy. "DAPPER: Learning Domain-Adapted Persona Representation Using Pretrained BERT and External Memory", The 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2020). 2020.
- Vijayaraghavan, Prashanth, Hugo Larochelle, and Deb Roy. "Interpretable Multi-Modal Hate Speech Detection." International Conference on Machine Learning, AI for Social Good Workshop, 2019.
- Vijayaraghavan, Prashanth, and Deb Roy. "Generating Black-Box Adversarial Examples for Text Classifiers Using a Deep Reinforced Model." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2019
- Chu, Eric*, Prashanth Vijayaraghavan*, and Deb Roy. "Learning Personas from Dialogue with Attentive Memory Networks." Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.
- Vijayaraghavan, Prashanth, and Deb Roy. "Video SemNet: Memory-Augmented Video Semantic Network." Proceedings of NIPS 2017 Workshop on Visually-Grounded Interaction and Language (ViGIL). 2017.
- Vijayaraghavan, Prashanth, et al. "TweetVista: An AI-Powered Interactive Tool for Exploring Conversations on Twitter." Proceedings of the 22nd International Conference on Intelligent User Interfaces Companion. ACM, 2017.
- Vosoughi, Soroush*, Prashanth Vijayaraghavan*, Ann Yuan, and Deb Roy. "Mapping Twitter Conversation Landscapes.", ICWSM. 2017.
- Vijayaraghavan, Prashanth*, Soroush Vosoughi*, and Deb Roy. "Twitter demographic classification using deep multi-modal multi-task learning." Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Vol. 2. 2017.
- Sra, M., Maes, P., Vijayaraghavan, P., & Roy, D. (2017, November). Auris: creating affective virtual spaces from music. In Proceedings of the 23rd ACM Symposium on Virtual Reality Software and Technology (p. 26). ACM.
- Sra, Misha, Prashanth Vijayaraghavan, Ognjen Rudovic, Pattie Maes, and Deb Roy. "DeepSpace: Mood-Based Image Texture Generation for Virtual Reality from Music." In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2289-2298. IEEE, 2017.
- Vosoughi, Soroush*, Prashanth Vijayaraghavan*, and Deb Roy. "Tweet2vec: Learning tweet embeddings using character-level cnn-lstm encoder-decoder." Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. ACM, 2016.
- Vijayaraghavan, Prashanth*, Soroush Vosoughi*, and Deb Roy. "Automatic Detection and Categorization of Election-Related Tweets." ICWSM. 2016.
- Vijayaraghavan, Prashanth, et al. "Deepstance at SemEval-2016 task 6: detecting stance in tweets using character and word-level CNNs." arXiv preprint arXiv:1606.05694, 2016.
- Vijayaraghavan, Prashanth. Automatic identification of representative content on Twitter. Diss. Massachusetts Institute of Technology, 2016.
- Vijayaraghavan, Prashanth, and Misha Sra. "Handwritten tamil recognition using a convolutional neural network." (2014).
*The authors contributed equally to this work.
- Washington Post: Twitter's political debate focuses on much different issues than Americans at large do
- Washington Post: How the Orlando attack showed the potential of an October Surprise
- Washington Post: Twitter users definitely see the Supreme Court vacancy as an election issue
- PRI: Just how uncivil is Election 2016? MIT's Media Lab has some charts you should see.
- New York Times: How to Escape Your Political Bubble for a Clearer View
- NPR: Tech Creates Our Political Echo Chambers. It Might Also Be A Solution
- Recode: This Chrome add-on lets you see Twitter through the eyes of other users
- Mashable: MIT-designed Chrome extension fixes your Twitter filter bubble
- The Outline: MIT released a tool that uses real people's Twitter feeds to show you the "other side"