• Publications
  • Influence
Sequence to Sequence -- Video to Text
A novel end- to-end sequence-to-sequence model to generate captions for videos that naturally is able to learn the temporal structure of the sequence of frames as well as the sequence model of the generated sentences, i.e. a language model. Expand
Integrating constraints and metric learning in semi-supervised clustering
Experimental results demonstrate that the unified approach produces better clusters than both individual approaches as well as previously proposed semi-supervised clustering algorithms. Expand
A probabilistic framework for semi-supervised clustering
A probabilistic model for semi-supervised clustering based on Hidden Markov Random Fields (HMRFs) that provides a principled framework for incorporating supervision into prototype-based clustering and experimental results demonstrate the advantages of the proposed framework. Expand
A Shortest Path Dependency Kernel for Relation Extraction
Experiments on extracting top-level relations from the ACE (Automated Content Extraction) newspaper corpus show that the new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels. Expand
Active Semi-Supervision for Pairwise Constrained Clustering
Experimental and theoretical results confirm that this active querying of pairwise constraints significantly improves the accuracy of clustering when given a relatively small amount of supervision. Expand
Semi-supervised Clustering by Seeding
Adaptive duplicate detection using learnable string similarity measures
This paper proposes to employ learnable text distance functions for each database field, and shows that such measures are capable of adapting to the specific notion of similarity that is appropriate for the field's domain. Expand
Content-boosted collaborative filtering for improved recommendations
This paper presents an elegant and effective framework for combining content and collaboration, which uses a content-based predictor to enhance existing user data, and then provides personalized suggestions through collaborative filtering. Expand
Learning to Parse Database Queries Using Inductive Logic Programming
Experimental results with a complete database-query application for U.S. geography show that CHILL is able to learn parsers that outperform a preexisting, hand-crafted counterpart, and provide direct evidence of the utility of an empirical approach at the level of a complete natural language application. Expand
Content-based book recommending using learning for text categorization
This work describes a content-based book recommending system that utilizes information extraction and a machine-learning algorithm for text categorization and shows initial experimental results demonstrate that this approach can produce accurate recommendations. Expand