Nguyen Bach

Latest

• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning
• ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition
• Image paragraph generator
• Image paragraph generator
• The innovation behind AI at Scale
• MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations
• Automated Concatenation of Embeddings for Structured Prediction
• Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
• Multi-View Cross-Lingual Structured Prediction with Minimum Supervision
• Risk Minimization for Zero-shot Sequence Labeling
• Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
• AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
• An Investigation of Potential Function Designs for Neural CRF
• More Embeddings, Better Sequence Labelers?
• Structure-Level Knowledge Distillation For Multilingual Sequence Labeling
• FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
• Noisy BiLSTM-Based Models for Disfluency Detection
• Unsupervised Multi-Modal Neural Machine Translation
• Alibaba Speech Translation Systems for IWSLT 2018
• Eye Tracking Using Video Information and Electrooculography Information
• The SDL Language Weaver Systems in the WMT12 Quality Estimation Shared Task
• TriS: A Statistical Sentence Simplifier with Log-linear Models and Margin-based Discriminative Training
• CMU Haitian Creole-English Translation System for WMT 2011
• Goodness: A Method for Measuring Machine Translation Confidence
• A Semi-Supervised Word Alignment Algorithm with Partial Manual Alignments
• Source-side Dependency Tree Reordering Models with Subtree Movements and Constraints
• Virtual Babel: Towards Context-Aware Machine Translation in Virtual Worlds
• Cohesive Constraints in A Beam Search Phrase-based Decoder
• Incremental Adaptation of Speech-to-Speech Translation
• Improving Word Alignment with Language Model Based Confidence Scores
• Recent Improvements in the CMU Large Scale Chinese-English SMT System
• A Log-Linear Block Transliteration Model based on Bi-Stream HMMs
• A Survey on Relation Extraction
• Handling OOV Words in Arabic ASR Via Flexible Morphological Constraints
• The CMU TransTac 2007 Eyes-free and Hands-free Two-way Speech-to-Speech Translation System
• The UKA-CMU Statistical Machine Translation Systems for IWSLT 2007
• The UKA/CMU Statistical Machine Translation System for IWSLT 2006
• Quantitative Analysis and Synthesis of Syllabic Tones in Vietnamese