Deep Learning in NLP and Beyond - 2015
Explore advanced machine learning in NLP, focusing on recurrent neural networks and deep learning. Gain insights into future research directions for developing language-understanding machines.
Combining AI and Crowd for Professional-Quality Translation at Scale
Explore how Unbabel combines AI and crowdsourcing to deliver fast, high-quality translations at scale, breaking down language barriers between companies and customers.
BitFunnel: How Bing Uses Bloom Filters for Search
Explore BitFunnel algorithm powering Bing search, using Bloom filters to efficiently process queries and search billions of documents, challenging conventional wisdom in text indexing.
The Ins and Outs of Preposition Semantics - 2017
Explore preposition semantics, their crucial role in linking meaning, and challenges in comprehensive annotation and cross-linguistic analysis. Gain insights into ongoing research and corpus development.
Learning Constraint-Based Grammars from Representative Data - 2008
Explore constraint-based grammars for natural language processing, integrating syntax, semantics, and learning. Discover a new grammar formalism for deep language understanding and its applications in knowledge acquisition.
Zipf's Law Suggests a Three-Pronged Approach to Inclusive Speech Recognition
Explore Zipf's law in speech recognition, from frequent words to OOV challenges. Discover how power-law distributions impact language technologies and inclusive ASR development for diverse communities.
Towards Fast Autonomous Learners: Advances in Reinforcement Learning - 2015
Explore reinforcement learning for AI agents interacting with humans, focusing on sample efficiency and transfer learning to improve educational tools and decision-making systems.
Low-resource Morphological Generation with Neural Sequence-to-Sequence Models
Explore neural sequence-to-sequence approaches for morphological generation in low-resource languages, including multi-task learning, cross-lingual transfer, and semi-supervised techniques.
I-Vector Representation Based on GMM and DNN for Audio Classification - 2015
Explore I-vector approach for audio classification, including GMM mean modeling and recent subspace techniques. Learn about applications in language and dialect recognition using deep neural networks.
8-bit Methods for Efficient Deep Learning
Explore 8-bit methods for efficient deep learning, focusing on quantization techniques, optimizers, and inference for large language models to improve efficiency without performance loss.
Target-Speaker Methods for Speech Recognition - Overlapping Speech Solutions
Explore advanced techniques for multi-talker ASR, including GPU-accelerated processing, wake-word leveraging, and self-supervised models to improve speech recognition in challenging environments.
Motion Magnification and Motion Denoising
Explore motion magnification and denoising techniques for video analysis and manipulation, including separating components and amplifying small movements in real-time applications.
Speech Production Features for Deep Neural Network Acoustic Modeling - 2015
Explore speech production knowledge for improved DNN acoustic modeling in ASR. Learn about vocal tract measurements and phonological embeddings to enhance recognition accuracy.
Speech Synthesis and Voice Conversion: Machine Learning Can Mimic Anyone's Voice
Explore cutting-edge voice conversion techniques, their potential, and limitations. Learn about speech synthesis advancements and resources for expressive voice conversion research.
Towards Large-Scale Natural Language Inference with Distributional Semantics
Explore natural language inference using distributional semantics, covering summarization, semantic models, and knowledge induction for advanced text analysis.
OUCH: Investigating Limitations of Hidden Markov Models in Speech Recognition
Explore speech recognition challenges, focusing on Hidden Markov Model limitations. Examine frame-to-frame independence assumptions and their implications for improving recognition accuracy.
Generative Agents: Interactive Simulacra of Human Behavior
Explore interactive simulations of human behavior using generative agents in a virtual village. Learn about memory streams, reflections, and planning for creating believable AI characters.
Building Helpful Language Models - Challenges and Solutions
Explore challenges and solutions in aligning language models, including self-instruction, source tracing, and web interaction. Gain insights into building robust, transparent AI systems for practical applications.
Automatic Detection and Monitoring of Parkinson's Disease from Language and Speech
Explore cutting-edge techniques for detecting and monitoring Parkinson's disease through speech and language analysis, presented by PhD student Anna Favaro from Johns Hopkins University.
Deep Learning for Protein Structure Discovery
Explore deep learning techniques for uncovering protein structures, revolutionizing molecular biology and drug discovery.
Representation and Metric Learning Advances for Face and Speaker Biometric Systems
Explore advances in representation and metric learning for face and speaker biometric systems, enhancing accuracy and efficiency in identity verification.