Markus Dreyer

Latest

• Analyzing the Abstractiveness-Factuality Tradeoff With Nonlinear Abstractiveness Constraints
• Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters
• Rewards with Negative Examples for Reinforced Topic-Focused Abstractive Summarization
• Transductive Learning for Abstractive News Summarization
• Multi-Task Networks with Universe, Group, and Task Feature Learning
• Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
• Transfer Learning for Neural Semantic Parsing
• Zero-Shot Learning Across Heterogeneous Overlapping Domains
• LatticeRnn: Recurrent Neural Networks Over Lattices
• hyp: A Toolkit for Representing, Manipulating, and Optimizing Hypergraphs
• APRO: All-Pairs Ranking Optimization for MT Tuning
• HyTER: Meaning-Equivalent Semantics for Translation Evaluation
• Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model
• A Non-Parametric Model for the Discovery of Inflectional Paradigms from Plain Text Using Graphical Models over Strings
• Hill climbing on speech lattices: A new rescoring framework
• Graphical Models over Multiple Strings
• HLTCOE Approaches to Knowledge Base Population at TAC 2009
• Latent-Variable Modeling of String Transductions with Finite-State Methods
• Machine Translation System Combination using ITG-based Alignments
• Comparing Reordering Constraints for SMT Using Efficient BLEU Oracle Computation
• Better Informed Training of Latent Syntactic Features
• Vine Parsing and Minimum Risk Reranking for Speed and Precision