Multimodal Information Access and Synthesis, a DHS-IDS Center of Excellence
Supported by MIAS
Period:
The goal of the Center for Multimodal Information Access and Synthesis Center (MIAS) at UIUC is to develop the fundamental theories, computational models, algorithms, and tools for analysts to access a variety of data formats and models, to integrate them with existing resources, and to transform raw data into useful and understandable information, in support of productive and efficient analysis.
We aim at extending the state-of-the-art and develop new technologies for: (1) Focused data retrieval and integration, to identify and collect relevant data from multiple modalities, (2) Semantic data enrichment, to allow navigation and search across disparate data modalities and augment knowledge bases by inferring semantics from unstructured data and images, (3) Entity identification and relationship discovery, to identify real-world entities and relate them to existing institutional resources, (4) Knowledge discovery and hypotheses generation and verification, to construct the rich semantic structure and hidden networks of entity linkages, and (5) Fundamental machine learning, database and data mining, natural language processing, and computer vision techniques required for and driven by the aforementioned problems.
Our educational mission is to develop diverse human resources to enhance the scientific research, educational, and governmental workforce in MIAS disciplines.
Our educational initiatives have been developed to encourage computer science students in universities with small research programs, particularly those that are minority serving; to pursue graduate studies at stronger institutions where they can make a bigger impact on the field; and to expose them to national labs.
Key to this effort is the Data Sciences Summer Institute (DSSI), a comprehensive education program for college juniors and seniors designed to increase participation in the study and practice of MIAS topics.
Relevant Publications:
- D. Roth and Y. Tu, Aspect Guided Text Categorization with Unobserved Labels. Proceedings of ICDM (2009) [bibitem]
- J. Pasternack and D. Roth, Learning Better Transliterations. The 18th ACM Conference on Information and Knowledge Management (CIKM) (2009) [bibitem]
- D. Roth, M. Sammons, and V. Vydiswaran, A Framework for Entailed Relation Recognition. Proc. of the Annual Meeting of the ACL (2009) [bibitem]
- A. Klementiev, D. Roth, K. Small, and I. Titov, Unsupervised Rank Aggregation with Domain-Specific Expertise. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI) (2009) [bibitem]
- L. Ratinov and D. Roth, Design Challenges and Misconceptions in Named Entity Recognition. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL) (2009) [bibitem]
- M. Chang, D. Goldwasser, D. Roth, and Y. Tu, Unsupervised Constraint Driven Learning For Transliteration Discovery. NAACL (2009) [bibitem]
- A. Klementiev, D. Roth, and K. Small, A Framework for Unsupervised Rank Aggregation. Proc. of the SIGIR Workshop on Learning to Rank for Information Retrieval (2008) pp. 32-39 [bibitem]
- M. Chang, L. Ratinov, and D. Roth, Constraints as Prior Knowledge. ICML Workshop on Prior Knowledge for Text and Language Processing (2008) pp. 32-39 [bibitem]
- M. Chang, L. Ratinov, D. Roth, and V. Srikumar, Importance of Semantic Represenation: Dataless Classification. Proceedings of the National Conference on Artificial Intelligence (AAAI) (2008) [bibitem]
- M. Chang, L. Ratinov, N. Rizzolo, and D. Roth, Learning and Inference with Constraints. Proceedings of the National Conference on Artificial Intelligence (AAAI) (2008) [bibitem]
- A. Klementiev, D. Roth, and K. Small, Unsupervised Rank Aggregation with Distance-Based Models. Proc. of the International Conference on Machine Learning (ICML) (2008) [bibitem]
- A. Klementiev, D. Roth, and K. Small, An Unsupervised Learning Algorithm for Rank Aggregation. Proc. of the European Conference on Machine Learning (ECML) (2007) [bibitem]
