Virgil Pavlu
Associate Teaching Professor
Research interests
- Information retrieval
- Machine learning
- Algorithms
Education
- PhD in Computer Science, Northeastern University
- BS in Mathematics with minor in Computer Science, University of Bucharest — Romania
Biography
Virgil Pavlu is an associate teaching professor at the Khoury College of Computer Sciences at Northeastern University. He earned his doctorate in computer science from Northeastern and his bachelor’s in mathematics from the University of Bucharest, Romania. Pavlu’s research interests include information retrieval, including diversity, learning to rank, metasearch, score distribution models, and relevance feedback. At Northeastern, he teaches machine learning, information retrieval, and algorithms.
Pavlu’s current research centers around machine learning algorithms for certain data types, particularly applications to text data. On long text, this includes the extraction and selection of n-grams features, and on short text, this includes the discovery, indexing and matching of nuggets for tasks like relevance and novelty. One of his projects addresses the representability of text documents in high-dimensional spaces, the study of similarity and distance notions, and the active learning application to crowdsourcing methodologies for obtaining such representation.
Since 2007, Pavlu has been involved with the SIGIR conference either as a reviewer or an organizer. He was a coordinator of several TREC and NTCIR tracks.
Pavlu grew up in Bucharest, Romania.
Recent publications
-
Don’t Just Pay Attention, PLANT It: Transfer L2R Models to Fine-tune Attention in Extreme Multi-Label Text Classification
Citation: Debjyoti Saharoy, Javed A. Aslam, Virgil Pavlu. (2024). Don't Just Pay Attention, PLANT It: Transfer L2R Models to Fine-tune Attention in Extreme Multi-Label Text Classification CoRR, abs/2410.23066. https://doi.org/10.48550/arXiv.2410.23066 -
A Complex KBQA System using Multiple Reasoning Paths
Citation: Kechen Qin, Yu Wang , Cheng Li, Kalpa Gunaratna, Hongxia Jin, Virgil Pavlu, Javed A. Aslam. (2020). A Complex KBQA System using Multiple Reasoning Paths CoRR, abs/2005.10970. https://arxiv.org/abs/2005.10970 -
Learning to Calibrate and Rerank Multi-label Predictions
Citation: Cheng Li, Virgil Pavlu, Javed A. Aslam, Bingyu Wang, Kechen Qin. (2019). Learning to Calibrate and Rerank Multi-label Predictions ECML/PKDD (3), 220-236. https://doi.org/10.1007/978-3-030-46133-1_14 -
Adapting RNN Sequence Prediction Model to Multi-label Set Prediction
Citation: Conference Proceedings Adapting RNN Sequence Prediction Model to Multi-label Set Prediction. Qin, Kechen; Li, Cheng; Pavlu, Virgil; Aslam, Javed. Proceedings of the 2019 NAACL-HLT, Volume 1 (Long and Short Papers), 2019 8 jun I Association for Computational Linguistics, Minneapolis, Minnesota -
A Study of Realtime Summarization Metrics
Citation: Matthew Ekstrand-Abueg, Richard McCreadie, Virgil Pavlu, and Fernando Diaz. 2016. A Study of Realtime Summarization Metrics. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management (CIKM '16). Association for Computing Machinery, New York, NY, USA, 2125–2130. DOI: 10.1145/2983323.2983653 -
Aggregation of Crowdsourced Ordinal Assessments and Integration with Learning to Rank: A Latent Trait Model
Citation: P. Metrikov, V. Pavlu, J. A. Aslam. "Aggregation of Crowdsourced Ordinal Assessments and Integration with Learning to Rank: A Latent Trait Model". Proceedings of the 24th ACM Conference on Information and Knowledge Management, Melbourne, Australia (2015). DOI: 10.1145/2806416.2806492 -
A Modification of LambdaMART to Handle Noisy Crowdsourced Assessments
Citation: Pavel Metrikov, Jie Wu, Jesse Anderton, Virgil Pavlu, and Javed A. Aslam. 2013. A Modification of LambdaMART to Handle Noisy Crowdsourced Assessments. In Proceedings of the 2013 Conference on the Theory of Information Retrieval (ICTIR '13). Association for Computing Machinery, New York, NY, USA, 133–134. https://doi.org/10.1145/2499178.2499198 -
Optimizing nDCG Gains by Minimizing Effect of Label Inconsistency
Citation: P. Metrikov, V. Pavlu, J. A. Aslam, "Optimizing nDCG Gains by Minimizing Effect of Label Inconsistency", Advances in Information Retrieval: 35th European Conference on IR Research (ECIR), Moscow, Russia (2013). Best Poster Paper Award -
Impact of Assessor Disagreement on Ranking Performance
Citation: P. Metrikov, V. Pavlu, J. A. Aslam, "Effect of Assessor Disagreement on Ranking Performance", Proceedings of the 35th international ACM SIGIR conference on Research and Development in Information Retrieval, Portland, USA (2012) -
A Large-scale Study of the Effect of Training Set Characteristics over Learning-to-Rank Algorithms
Citation: E. Kanoulas, S. Savev, P. Metrikov, V. Pavlu, J. A. Aslam, "A Large-scale Study of the Effect of Training Set Characteristics over Learning-to-Rank Algorithms", Proceedings of the 34th international ACM SIGIR conference on Research and Development in Information Retrieval, Beijing, China (2011)