Markus Dreyer

Latest

• Deep Research Comparator: A Platform for Fine-Grained Human Annotations of Deep Research Agents
• Meaning Summarization Techniques
• NeoQA: Evidence-Based Question Answering with Generated News Events
• RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
• CCSum: A Large-Scale and High-Quality Dataset for Abstractive News Summarization
• NewsQs: Multi-Source Question Generation for the Inquiring Mind
• RefineSumm: Self-Refining MLLM for Generating a Multimodal Summarization Dataset
• Unified Embeddings for Multimodal Retrieval via Frozen LLMs
• Enhancing Multi-Document Summarization with Cross-Document Graph-based Information Extraction
• Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization
• Faithfulness-Aware Decoding Strategies for Abstractive Summarization
• Background Summarization of Event Timelines
• Generating Summaries with Controllable Readability Levels
• On Conditional and Compositional Language Model Differentiable Prompting
• Efficient Few-Shot Fine-Tuning for Opinion Summarization
• FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations
• 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
• Word Embeddings for Natural Language Processing
• Voice User Interface Knowledge Acquisition System
• Multi-Task Networks with Universe, Group, and Task Feature Learning
• Extendable Label Recognition of Linguistic Input
• Lattice Decoding and Result Confirmation Using Recurrent Neural Networks
• Lattice Encoding Using Recurrent Neural Networks
• Method and System for Automatic Management of Reputation of Translators
• Method and System for Automatic Management of Reputation of Translators
• Neural Latent Variable Model for Spoken Language Understanding
• Speech Processing with Learned Representation of User Interaction History
• 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