Neural Nets for NLP 2020 - Neural Nets + Knowledge Bases
Explore methods for learning knowledge bases from neural embeddings and incorporating them into neural models. Covers relation extraction, distant supervision, and reasoning over text corpora as knowledge bases.
Neural Nets for NLP 2020 - Document Level Models
Explore document-level NLP techniques including language modeling, coreference resolution, and discourse parsing. Learn advanced approaches for handling long-range dependencies and entity relationships in text.
CMU Neural Nets for NLP 2020 - Multitask and Multilingual Learning
Explore multitask and multilingual learning in NLP, covering methods, objectives, and challenges. Gain insights into cross-lingual transfer, data balancing, and zero-shot approaches.
Neural Nets for NLP 2020 - Unsupervised and Semi-supervised Learning of Structure
Explore unsupervised and semi-supervised learning methods for NLP, covering feature learning, structure learning, and design decisions with practical examples and applications.
Neural Nets for NLP 2020 - Search-Based Structured Prediction
Learn search-based structured prediction techniques for NLP, including structured perceptron, max-margin objectives, and exposure bias remedies. Explore global models and cost-augmented training for improved sequence prediction.
Neural Nets for NLP 2020: Advanced Search Algorithms
Explore advanced search algorithms for NLP, including beam search, minimum Bayes risk, and sampling-based methods. Learn to address search errors and model errors in neural networks.
Neural Nets for NLP - Minimum Risk Training and Reinforcement Learning
Explore minimum risk training and reinforcement learning in NLP, covering error analysis, policy gradients, and value-based methods to enhance neural network performance.
Neural Nets for NLP 2020 - Generating Trees Incrementally
Explore transition-based parsing, shift-reduce parsing with neural networks, stack LSTMs, and semantic parsing for natural language processing applications.
Neural Nets for NLP - Debugging Neural Nets
Learn techniques for identifying and resolving issues in neural networks for NLP, covering training and test-time problems, optimization strategies, and performance analysis.
CMU Neural Nets for NLP - Distributional Semantics and Word Vectors
Explore distributional semantics and word vectors in NLP, covering techniques like skip-grams, CBOW, and advanced methods for creating and evaluating word embeddings.
Neural Nets for NLP 2020 - Language Modeling, Efficiency/Training Tricks
Explore neural language models, optimization techniques, and evaluation metrics for NLP. Learn about feed-forward networks, overfitting prevention, and automatic optimization methods.
Neural Nets for NLP 2019 - Advanced Search Algorithms
Explore advanced search algorithms for NLP, including beam search, A* search, and search with future costs. Learn techniques to improve efficiency and effectiveness in natural language processing tasks.
Neural Nets for NLP - Multi-task, Multi-lingual Learning
Explore multi-task and multi-lingual learning in NLP, covering feature extraction, pre-training encoders, parameter adaptation, and structured prediction across languages.
Neural Nets for NLP 2019 - Models of Dialog
Learn about chat-based and task-based dialog models, covering generation, retrieval, and task completion approaches. Explore neural architectures, evaluation methods, and techniques for improving coherence and personality in dialog systems.
Neural Nets for NLP 2019 - Unsupervised and Semi-supervised Learning of Structure
Explore unsupervised and semi-supervised learning methods for NLP, covering feature and structure learning, design decisions, and practical examples in this advanced lecture.
CMU Multilingual NLP - The LORELEI Project
Explore rapid development of low-resource information extraction in new languages, focusing on the LORELEI project's techniques, challenges, and real-world applications in disaster scenarios.
CMU Multilingual NLP - Syntax and Parsing
Explore syntax, dependency parsing, and linguistic discovery with AutoLex. Learn about major word orders, parsing models, and tools for multilingual NLP research and applications.
CMU Multilingual NLP 2022 - Unsupervised Machine Translation
Explore unsupervised machine translation techniques, including initialization methods, word translation, and back-translation, for scenarios without parallel data.
CMU Multilingual NLP 2022 - Data-Driven Strategies for NMT
Explore data-driven strategies for neural machine translation, including evaluation methods, data augmentation techniques, and approaches for high and low-resource languages.
CMU Multilingual NLP 2022 - Translation and Translation Data
Explore machine translation, evaluation metrics, and data sources in this comprehensive lecture on multilingual NLP, covering industry practices and challenges in translation.
CMU Multilingual NLP 2022 - Typology
Explore language similarities, families, and typology. Learn about databases like WALS and techniques for typology prediction and language transfer in multilingual NLP.