Interpretability & Analysis: Modern NLP

Related lectures (32)

Page 3 of 4

Explores the evolution of protein structure prediction with AlphaFold models and introduces OpenFold insights.

Explores the attention mechanism in machine translation, addressing the bottleneck problem and improving NMT performance significantly.

Delves into neuro-symbolic representations for commonsense knowledge and reasoning in natural language processing applications.

Showcases a student's internship at Deezer's research team working on natural language processing.

Covers the pretraining of sequence-to-sequence models, focusing on BART and T5 architectures.

Covers an internship report at Tencent Al lab, focusing on 3D avatar reconstruction and neural rendering techniques.

Introduces deep learning concepts for NLP, covering word embeddings, RNNs, and Transformers, emphasizing self-attention and multi-headed attention.

Reviews language models, tokenization, and probability estimation in NLP systems.

Explores prompting, alignment, and the capabilities of large language models for natural language processing tasks.

Explores the efficiency of training large language models and the environmental impact of AI.