Learning with a Human-in-the-Loop: Tandem Learning (Learning on Both Features and Instances) (phD thesis), Interactive Clustering etc.
Normalizing names in ASR output for speech Indexing and Retrieval.Hema Raghavan, Omid Madani, Rosie Jones, " Active Learning on Both Features and Instances," JMLR-06 (Journal of Machine Learning Research) 7 (Aug)pp. 1655-1686.
Hema Raghavan, Omid Madani, Rosie Jones, "InterActive Feature Selection," in the Proceedings of IJCAI-05, pp. 841-846.
Ron Bekkerman, Hema Raghavan, James Allan and Koji Eguchi, " Interactive Clustering of Text Collections According to any User-Specified Criterion, " Proceedings of IJCAI07, Hyderabad, India
Hema Raghavan " Tandem Learning: A New Learning Framework for Document Categorization , " PhD Thesis
Hema Raghavan and James Allan, "Matching Inconsistently Spelled Names in Automatic Speech Recognizer Output for Information Retrieval," in the Proceedings of HLT/EMNLP 2005, pp. 451-458.
Hema Raghavan and James Allan, "Using Soundex Codes for indexing ASR documents," in the Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004, pp. 22-27.
Topic Detection and Tracking
Margaret Connell, Ao Feng, Giridhar Kumaran, Hema Raghavan, Chirag Shah, James Allan, "UMass at TDT 2004," in the Proceedings of TDT 2004, Gaithersburg, MD
Allan J., et al, "U-Mass TDT 2003 Research Summary", in in the Notebook Proceedings of TDT 2003 Workshop
Data mining in social networks from semi-structured data with James Allan and Andrew McCallum.
Hema Raghavan, James Allan, Andrew McCallum, "An Exploration of Entity Models, Collective Classification and Relation Description," in Proceedings of the Second International Workshop on Link Analysis and Group Detection, LinkKDD2004, August 22, 2004 in conjunction with the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, USA, pp 1-10.
This work is expanded in CIIR Technical Report IR-275
Using Part of Speech Patterns to Reduce Query Ambiguity with James Allan.
Allan, J. and Raghavan, H., "Using Part-of-speech Patterns to Reduce Query Ambiguity," in SIGIR 2002, pp. 307-314.