Description

Stanford Natural Language Processing with Deep Learning 2017

Stanford Natural Language Processing with Deep Learning 2017

English | Size: 7.32 GB Category: Tutorial
Natural language processing (NLP) is one of the most important technologies of the information age. Understanding complex language utterances is also a crucial part of artificial intelligence. Applications of NLP are everywhere because people communicate most everything in language: web search, advertisement, emails, customer service, language translation, radiology reports, etc. There are a large variety of underlying tasks and machine learning models behind NLP applications. Recently, deep learning approaches have obtained very high performance across many different NLP tasks. These models can often be trained with a single end-to-end model and do not require traditional, task-specific feature engineering.
In this winter quarter course students will learn to implement, train, debug, visualize and invent their own neural network models. The course provides a thorough introduction to cutting-edge research in deep learning applied to NLP. On the model side we will cover word vector representations, window-based neural networks, recurrent neural networks, long-short-term-memory models, recursive neural networks, convolutional neural networks as well as some recent models involving a memory component. Through lectures and programming assignments students will learn the necessary engineering tricks for making neural networks work on practical problems.
This course is a merger of Stanford’s previous cs224n course (Natural Language Processing) and cs224d (Deep Learning for Natural Language Processing)

Natural language processing (NLP) is one of the most important technologies of the information age. Understanding complex language utterances is also a crucial part of artificial intelligence. Lecture Series on Natural Language Processing with Deep Learning introduces core NLP tasks and their deep learning models. Tasks discussed include: separating sentences from texts in discourse, named entity recognition, tagging parts of speech and defining syntactic structures, and semantic role labeling.

In this class, we will cover various natural language processing models and applications, and how deep learning approaches can build these models. We will also cover several topics related to deep learning such as convolutional neural networks, recurrent neural networks, sequence-to-sequence models, long short-term memory units and attention mechanisms.

Stanford Natural Language Processing with Deep Learning is a premier text that bridges the gap between basic introductions to NLP and cutting-edge research. Through detailed examples and exercises, it explains how deep learning techniques can be applied to a variety of NLP tasks. It includes an introduction to deep learning models and error analysis techniques alongside more advanced material on state-of-the-art techniques such as neural sequence transduction models and neural question answering.

Stanford Natural Language Processing with Deep Learning provides an introduction and in-depth look at the state of the art in deep learning methods for language understanding. You’ll learn about key concepts, strategies, and applications for each task. Learn about word meanings, syntactic parsing, question answering and dialogue processing.

This course provides an introduction to natural language processing (NLP) with deep learning, covering key NLP tasks and topics such as: Part of speech tagging (POS), named entity recognition (NER), parsing, sentiment analysis, phrase-level classification, question answering (QA) and more. Tasks include syntactic parsing from Stanford Parser and automatic semantic role labeling based on WordNet ontology.