深度学习NLP相关资源大列表

点击上方 “机器学习研究会”可以订阅

摘要

 

转自：爱可可-爱生活

Contents

• Courses 

• Books

• Tutorials / Demos

• Talks / Lectures

• Frameworks

• Papers

• Blog Posts

• Researchers

• Datasets

• Miscellaneous

• Contributing

Courses

1. CS224d: Deep Learning for Natural Language Processing from Stanford

• Course homepage A complete survey of the field with videos, lecture slides, and sample student projects.

• Course Lectures Video playlist.

• Course notes Probably the best "book" on DL for NLP.

2. Neural Networks for NLP from Carnegie Mellon University

• Coures homepage

• Course Lectures

• Course code

Books

1. Neural Network Methods in Natural Language Processing by Yoav Goldberg and Graeme Hirst

2. Deep Learning in Natural Language Processing by Li Deng and Dang Liu

3. Natural Language Processing in Action by Hobson Lane, Cole Howard, and Hannes Hapke

Tutorials

1. Deep Learning for Natural Language Processing (without Magic)

2. A Primer on Neural Network Models for Natural Language Processing

3. Deep Learning for Natural Language Processing: Theory and Practice (Tutorial)

4. TensorFlow Tutorials

5. Practical Neural Networks for NLP from EMNLP 2016 using DyNet framework

6. Recurrent Neural Networks with Word Embeddings

7. LSTM Networks for Sentiment Analysis

8. TensorFlow demo using the Large Movie Review Dataset

9. LSTMVis: Visual Analysis for Recurrent Neural Networks

Talks

1. Ali Ghodsi's lecture on word2vec part 1 and part 2

2. Richard Socher's talk on sentiment analysis, question answering, and sentence-image embeddings

3. Deep Learning, an interactive introduction for NLP-ers

4. Deep Natural Language Understanding

5. Deep Learning Summer School, Montreal 2016 Includes state-of-art language modeling.

Frameworks

1. Keras - The Python Deep Learning library Emphasis on user friendliness, modularity, easy extensibility, and Pythonic.

2. TensorFlow - A cross-platform, general purpose Machine Intelligence library with Python and C++ API.

3. Genism: Topic modeling for humans - A Python package that includes word2vec and doc2vec implementations.

4. DyNet - The Dynamic Neural Network Toolkit "work well with networks that have dynamic structures that change for every training instance".

5. Google’s original word2vec implementation

6. Deeplearning4j’s NLP framework - Java implementation.

7. deepnl - A Python library for NLP based on Deep Learning neural network architecture.

Papers

1. Deep or shallow, NLP is breaking out - General overview of how Deep Learning is impacting NLP.

2. Natural Language Processing from Research at Google - Not all Deep Learning (but mostly).

3. Distributed Representations of Words and Phrases and their Compositionality - The original word2vec paper.

4. word2vec Parameter Learning Explained

5. Distributed Representations of Sentences and Documents

6. Context Dependent Recurrent Neural Network Language Model

7. Translation Modeling with Bidirectional Recurrent Neural Networks

8. Contextual LSTM (CLSTM) models for Large scale NLP tasks

9. LSTM Neural Networks for Language Modeling

10. Exploring the Limits of Language Modeling

11. Conversational Contextual Cues - Models context and participants in conversations.

12. Sequence to sequence learning with neural networks

13. Efficient Estimation of Word Representations in Vector Space

14. Learning Character-level Representations for Part-of-Speech Tagging

15. Representation Learning for Text-level Discourse Parsing

16. Fast and Robust Neural Network Joint Models for Statistical Machine Translation

17. Parsing With Compositional Vector Grammars

18. Smart Reply: Automated Response Suggestion for Email

19. Neural Architectures for Named Entity Recognition - State-of-the-art performance in NER with bidirectional LSTM with a sequential conditional random layer and transition-based parsing with stack LSTMs.

20. GloVe: Global Vectors for Word Representation - A "count-based"/co-occurrence model to learn word embeddings.

21. Grammar as a Foreign Language - State-of-the-art syntactic constituency parsing using generic sequence-to-sequence approach.

22. Skip-Thought Vectors - "unsupervised learning of a generic, distributed sentence encoder"

• Paper

• Code

Blog Posts

1. the morning paper: The amazing power of word vectors - Overview of word vectors.

2. Deep Learning, NLP, and Representations

3. The Unreasonable Effectiveness of Recurrent Neural Networks

4. Machine Learning for Emoji Trends

5. Teaching Robots to Feel: Emoji & Deep Learning

6. Computational Linguistics and Deep Learning - Opinion piece on how Deep Learning fits into the broader picture of text processing.

Researchers

1. Christopher Manning

2. Ali Ghodsi

3. Richard Socher

4. Yoshua Bengio

Datasets

1. Dataset from "One Billion Word Language Modeling Benchmark" - Almost 1B words, already pre-processed text.

Miscellaneous

1. word2vec analogy demo

链接：

https://github.com/brianspiering/awesome-dl4nlp

原文链接：

https://m.weibo.cn/1402400261/4152655146704101

“完整内容”请点击【阅读原文】

↓↓↓