Natural Language Processing

In Natural Language Processing (NLP), we focus on how computers understand and interact with humans through natural conversation and text. We develop new NLP methods for collecting, processing, analyzing and understanding large amounts of natural language data for diverse applications such as intelligent conversational assistants, natural language search, document intelligence and knowledge acquisition.  

Our research projects span natural language understanding, dialogue systems, document semantics and affect understanding, document re-synthesis, text-mining, structured information extraction, knowledge acquisition and representation, joint language and vision-based understanding of images and videos, deep learning, and the use of natural language for computational creativity.  Our work includes efforts in intelligent assistants, multimodal search, document understanding, content generation, affect modelling, and multimodal content synthesis.  

Meet some of our researchersView More

Ruiyi Zhang

Research Scientist

Vlad Morariu

Senior Research Scientist

Koustava Goswami

Research Scientist

View our latest publicationsView More

Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation

Xing, L., Tran, Q., Heilbron, F., Dernoncourt, F., Yoon, D., Wang, Z., Bui, T., Carenini, G. (Feb. 2, 2024)

International Conference on Multimedia Modeling

Aspect-based Meeting Transcript Summarization: A Two-Stage Approach with Weak Supervision on Sentence Classification

Deng, Z., Yoon, D., Bui, T., Dernoncourt, F., Tran, Q., Liu, S., Zhao, W., Zhang, T., Wang, Y., Yu, P. (Dec. 18, 2023)

2023 IEEE International Conference on Big Data

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

Lai, V., Nguyen, C., Ngo, N., Nguyen, T., Dernoncourt, F., Rossi, R., Nguyen, T. (Dec. 10, 2023)

EMNLP 2023 Demonstrations

Knowledge Graphs

At Adobe Research, research scientists are exploring new ways of using knowledge graphs to develop tools to inform and inspire our customers. Knowledge graphs represent complex real-world material in a rich, interconnected network, helping users find answers that might otherwise be hidden.

View our latest newsView All News

Join us!

We are looking for researchers, engineers, and interns to take our technologies to the next level. We're recruiting, and we would love to hear from you!