Varun Manjunatha is a Research Scientist at Document Intelligence Lab, Adobe Research, Maryland, since January 2019. His research interests are at the intersection of Computer Vision and Natural Language Processing. He received his Ph.D from the Computer Science department at the University of Maryland, College Park, under the supervision of Prof. Larry Davis. He is a recipient of the John Gannon Fellowship and his work has been covered by MIT Tech Review, Digital Trends, etc. In his spare time, he enjoys reading, playing the piano, quiz bowl and exploring trails on his bicycle.

More information and publications can be found here :


Keyphrase Prediction from Video Transcripts: New Dataset and Directions

Veyseh, A., Tran, Q., Yoon, D., Manjunatha, V., Deilamsalehy, H., Jain, R., Bui, T., Chang, W., Dernoncourt, F., Nguyen, T. (Oct. 17, 2022)


Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text

Veyseh, A., Xu, N., Tran, Q., Manjunatha, V., Dernoncourt, F., Nguyen, T. (May. 27, 2022)

Findings of ACL 2022

IGA: An Intent-Guided Authoring Assistant

Sun, S., Zhao, W., Manjunatha, V., Jain, R., Morariu, V., Dernoncourt, F., Srinivasan, B., Iyyer, M. (Nov. 9, 2021)

EMNLP 2021

Syntopical Graphs for Computational Argumentation Tasks

Barrow, J., Jain, R., Lipka, N., Dernoncourt, F., Morariu, V., Manjunatha, V., Oard, D., Resnik, P., Wachsmuth, H. (Aug. 4, 2021)

ACL 2021

Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models

Du, M., Manjunatha, V., Jain, R., Deshpande, R., Dernoncourt, F., Gu, J., Sun, T., Hu, X. (Jun. 11, 2021)

NAACL 2021

Inducing Rich Interaction Structures between Words for Document-level Event Argument Extraction

Veyseh, A., Dernoncourt, F., Tran, Q., Manjunatha, V., Wang, L., Jain, R., Kim, D., Chang, W., Nguyen, T. (May. 14, 2021)

PAKDD 2021

Cross-Domain Document Object Detection: Benchmark Suite and Method

Li, K., Wigington, C., Tensmeyer, C., Zhao, H., Barmpalios, N., Morariu, V., Manjunatha, V., Sun, T., Fu, Y. (Jun. 22, 2020)

Conference on Computer Vision and Pattern Recognition (CVPR)