Difference between revisions of "Natural Language Processing (NLP)"
(→Evaluation Measures - Classification Performance) |
|||
| Line 5: | Line 5: | ||
* [http://en.wikipedia.org/wiki/Grammar_induction Grammar Induction | Wikipedia] | * [http://en.wikipedia.org/wiki/Grammar_induction Grammar Induction | Wikipedia] | ||
* [[Natural Language Tools]] | * [[Natural Language Tools]] | ||
| − | |||
* [[Global Vectors for Word Representation (GloVe)]] | * [[Global Vectors for Word Representation (GloVe)]] | ||
| − | |||
* [[Doc2Vec]] | * [[Doc2Vec]] | ||
* [[Bag-of-Words (scikit-learn: Count Vectorizer)]] | * [[Bag-of-Words (scikit-learn: Count Vectorizer)]] | ||
| Line 13: | Line 11: | ||
* [[Autoencoders / Encoder-Decoders]] | * [[Autoencoders / Encoder-Decoders]] | ||
* [[AI-Powered Search]] | * [[AI-Powered Search]] | ||
| − | + | ||
* [[Deep Q Learning (DQN)]] | * [[Deep Q Learning (DQN)]] | ||
* [http://www.chrisumbel.com/article/node_js_natural_language_nlp Natural Language | Chris Umbel] | * [http://www.chrisumbel.com/article/node_js_natural_language_nlp Natural Language | Chris Umbel] | ||
| Line 27: | Line 25: | ||
** [http://www.class-central.com/course/deep-learning-for-natural-language-processing-8097 Deep Learning for Natural Language Processing | Oxford - Phil Blunsom] | ** [http://www.class-central.com/course/deep-learning-for-natural-language-processing-8097 Deep Learning for Natural Language Processing | Oxford - Phil Blunsom] | ||
| − | + | ||
| Line 91: | Line 89: | ||
== Coreference == | == Coreference == | ||
[http://www.youtube.com/results?search_query=Coreference+nlp+natural+language Youtube search...] | [http://www.youtube.com/results?search_query=Coreference+nlp+natural+language Youtube search...] | ||
| + | |||
| + | * [[Neural Coreference]] | ||
<youtube>46ZoyPX-9gI</youtube> | <youtube>46ZoyPX-9gI</youtube> | ||
Revision as of 22:52, 22 September 2018
- How do I learn Natural Language Processing? | Sanket Gupta
- Natural Language Processing | Wikipedia
- Grammar Induction | Wikipedia
- Natural Language Tools
- Global Vectors for Word Representation (GloVe)
- Doc2Vec
- Bag-of-Words (scikit-learn: Count Vectorizer)
- Latent Dirichlet Allocation (LDA)
- Autoencoders / Encoder-Decoders
- AI-Powered Search
- Deep Q Learning (DQN)
- Natural Language | Chris Umbel
- NLP News | Sebastian Ruder
- 7 types of Artificial Neural Networks for Natural Language Processing
- Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts | Xingyou Wang, Weijie Jiang, Zhiyong Luo
- Language services | Cognitive Services | Microsoft Azure
- Text Transfer Learning
Speech recognition, speech translation, understanding complete sentences, understanding synonyms of matching words, sentiment analysis, and writing complete grammatically correct sentences and paragraphs.
Contents
- 1 Regular Expressions (Regex)
- 2 Tokenization / Sentence Splitting
- 3 Stop Words
- 4 Stemming
- 5 Part-of-Speech (POS) Tagging
- 6 Chunking
- 7 Chinking
- 8 Named Entity Recognition (NER)
- 9 Coreference
- 10 Hierarchical Classifier
- 11 Lemmatization
- 12 Corpora
- 13 Topic Modeling
- 14 Word Embeddings
- 15 Summarizer
- 16 Ontologies
- 17 Semantic Role Labeling (SRL)
- 18 Deep Learning Algorithms
- 19 Pipeline
- 20 Evaluation Measures - Classification Performance
- 21 Capabilities
Regular Expressions (Regex)
Search for text patterns, validate emails and URLs, capture information, and use patterns to save development time.
Tokenization / Sentence Splitting
Stop Words
Stemming
Part-of-Speech (POS) Tagging
Chunking
Chinking
Named Entity Recognition (NER)
Coreference
Hierarchical Classifier
Lemmatization
Corpora
Topic Modeling
Word Embeddings
Summarizer
Ontologies
(aka knowledge graph) can incorporate computable descriptions that can bring insight in a wide set of compelling applications including more precise knowledge capture, semantic data integration, sophisticated query answering, and powerful association mining - thereby delivering key value for health care and the life sciences.
Semantic Role Labeling (SRL)
identifies shallow semantic information in a given sentence. The tool labels verb-argument structure, identifying who did what to whom by assigning roles that indicate the agent, patient, and theme of each verb to constituents of the sentence representing entities related by the verb.
Deep Learning Algorithms
Pipeline
Evaluation Measures - Classification Performance
Confusion Matrix, Precision, Recall, F Score, ROC Curves, trade off between True Positive Rate and False Positive Rate.
Capabilities
Wikifier
