Nikhita Vedula
Abstract
Nikhita Vedula is an Applied Scientist at Amazon Alexa Science. She obtained her PhD in Computer Science and Engineering from the Ohio State University in August 2020, advised by Professor Srinivasan Parthasarathy. She received her bachelor's degree from the National Institute of Technology, Nagpur, India in 2015. Her research interests are at the intersection of data mining, natural language processing and social computing. Over the course of her PhD, her research involved designing efficient and novel machine learning and computational linguistic techniques that extract, interpret and transform the vast, unstructured digital content into structured knowledge representations in diverse contexts. She has worked with researchers from interdisciplinary fields such as emergency response, marketing, sociology and psychology. She performed research internships at Nokia Bell Laboratories, Adobe Research and Amazon Alexa AI. Her work has been published at several top data mining conferences such as the Web Conference, SIGIR, WSDM and ICDM. Her work on detecting user intentions from their natural language interactions won the Best paper award at the Web Conference 2020. She was a recipient of a Graduate Research Award (2020), a Presidential Fellowship (2019) and a University Graduate Fellowship (2015) at the Ohio State University. She was also selected as a Rising Star in EECS (2019).
- Caruana, R. 1997. Multitask learning. Machine learning 28, 1, 41--75.Google Scholar
- Devlin, J., Chang, M., Lee, K., and Toutanova, K. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint 1810.04805.Google Scholar
- Hochreiter, S. and Schmidhuber, J. 1997. Long short-term memory. In Neural computation.Google Scholar
- Leech, G. N. 2016. Principles of pragmatics. Routledge.Google Scholar
- Lipka, N. and Vedula, N. 2020. Utilizing recurrent neural networks to recognize and extract open intent from text inputs. US Patent App. 16/216, 296.Google Scholar
- Purohit, H., Vedula, N., Krishnaprasad, T., and Parthasarathy, S. 2018. Modeling transportation uncertainty in matching help seekers and suppliers during disasters. In InTI workshop at SIGIR.Google Scholar
- Searle, J. R. 1969. Speech acts: An essay in the philosophy of language. Cambridge university press.Google Scholar
- Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., et al. 2017. Attention is all you need. In NeurIPS.Google Scholar
- Vedula, N., Gupta, R., Alok, A., and Sridhar, M. 2020. Automatic discovery of novel intents & domains from text utterances. arXiv preprint arXiv:2006.01208.Google Scholar
- Vedula, N., Lipka, N., Maneriker, P., and Parthasarathy, S. 2020. Open intent extraction from natural language interactions. In The Web Conference (WWW).Google Scholar
- Vedula, N., Maneriker, P., and Parthasarathy, S. 2019. Bolt-k: Bootstrapping ontology learning via transfer of knowledge. In The Web Conference (WWW).Google Scholar
- Vedula, N., Nicholson, P. K., Ajwani, D., Dutta, S., Sala, A., and Parthasarathy, S. 2018. Enriching taxonomies with functional domain knowledge. In ACM Conference on Research & Development in Information Retrieval (SIGIR).Google Scholar
- Vedula, N. and Parthasarathy, S. 2017. Emotional and linguistic cues of depression from social media. In ACM Digital Health (DH).Google Scholar
- Vedula, N. and Parthasarathy, S. 2021. Face-keg: Fact checking explained using knowledge graphs. In ACM International Conference on Search and Data Mining (WSDM).Google Scholar
- Vedula, N., Parthasarathy, S., and Shalin, V. L. 2016. Predicting trust relations among users in a social network: On the role of influence, cohesion and valence. In WISDOM workshop at SIGKDD.Google Scholar
- Vedula, N., Parthasarathy, S., and Shalin, V. L. 2017. Predicting trust relations within a social network: A case study on emergency response. In ACM Web Science Conference (WebSci'17).Google Scholar
- Vedula, N., Sun, W., Lee, H., Gupta, H., Ogihara, M., Johnson, J., Ren, G., and Parthasarathy, S. 2017a. Multimodal content analysis for effective advertisements on youtube. In IEEE International Conference on Data Mining (ICDM).Google Scholar
- Vedula, N., Sun, W., Lee, H., Gupta, H., Ogihara, M., Johnson, J., Ren, G., and Parthasarathy, S. 2017b. Multimodal content analysis for effective advertisements on youtube. arXiv:1709.03946 (extended version of ICDM paper).Google Scholar
Recommendations
Society of Modeling and Simulation (SCS) Election
The results of the recent SCS election of Board Members are as follows:
President: David Cook, Stephen F. Austin State University, USA
President-Elect: Jerry Couretas, Lockheed Martin, USA, and Editor-in-Chief of The Journal of Defense Modeling and ...
"Context-aware access control and presentation for linked data" by Luca Costabello with Prateek Jain as coordinator
Luca Costabello is a postdoctoral fellow in the Fujitsu Linked Data Research Team in Galway, Ireland. His research interests span linked data consumption, the ubiquitous web of data, and access control for graph stores. He obtained a PhD in computer ...
Comments