Difference between revisions of "Natural Language Processing (NLP)"
| Line 35: | Line 35: | ||
<youtube>lCRs-Xn0Af8</youtube> | <youtube>lCRs-Xn0Af8</youtube> | ||
<youtube>DDByc9LyMV8</youtube> | <youtube>DDByc9LyMV8</youtube> | ||
| − | + | ||
| − | + | ||
| − | |||
| − | |||
== Regular Expressions (Regex)== | == Regular Expressions (Regex)== | ||
| Line 78: | Line 76: | ||
<youtube>VrT3TRDDE4M</youtube> | <youtube>VrT3TRDDE4M</youtube> | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
== Hierarchical Dataless Classifier == | == Hierarchical Dataless Classifier == | ||
| Line 107: | Line 94: | ||
== Word Embeddings == | == Word Embeddings == | ||
[http://www.youtube.com/results?search_query=word+embeddings+nlp+natural+language Youtube search...] | [http://www.youtube.com/results?search_query=word+embeddings+nlp+natural+language Youtube search...] | ||
| + | |||
| + | <youtube>KMoZdMyv9z8</youtube> | ||
| + | |||
| + | == Wikifier == | ||
| + | [http://www.youtube.com/results?search_query=Wikifier+nlp+natural+language Youtube search...] | ||
<youtube>VrT3TRDDE4M</youtube> | <youtube>VrT3TRDDE4M</youtube> | ||
| Line 116: | Line 108: | ||
* [[GRU]] | * [[GRU]] | ||
| − | <youtube> | + | <youtube>p5K_xtldcp4</youtube> |
== Summarizer == | == Summarizer == | ||
| Line 123: | Line 115: | ||
<youtube>ogrJaOIuBx4</youtube> | <youtube>ogrJaOIuBx4</youtube> | ||
<youtube>0DLa5sApXhc</youtube> | <youtube>0DLa5sApXhc</youtube> | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
== Ontologies == | == Ontologies == | ||
| Line 136: | Line 123: | ||
<youtube>WayalrOkCkY</youtube> | <youtube>WayalrOkCkY</youtube> | ||
<youtube>k5X12mdEvb8</youtube> | <youtube>k5X12mdEvb8</youtube> | ||
| + | |||
| + | == Semantic Role Labeling (SRL) == | ||
| + | [http://www.youtube.com/results?search_query=Semantic+Role+Labeling+nlp+natural+language Youtube search...] | ||
| + | |||
| + | * [http://cogcomp.org/page/software_view/SRL Illinois Semantic Role Labeler (SRL) | Cognitive Computation Group] | ||
| + | ** [http://cogcomp.org/page/demo_view/SRL Semantic Role Labeling Demo] | ||
| + | |||
| + | 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. | ||
| + | |||
| + | <youtube>3OFqz-4DKJQ</youtube> | ||
| + | <youtube>aptipHMTmmk</youtube> | ||
| + | <youtube>yzzxOiXX5_Q</youtube> | ||
| + | <youtube>C555PBoUlrw</youtube> | ||
| + | |||
== Pipeline == | == Pipeline == | ||
Revision as of 10:44, 22 September 2018
- How do I learn Natural Language Processing? | Sanket Gupta
- Natural Language Processing | Wikipedia
- Grammar Induction | Wikipedia
- Natural Language Tools
- Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Recurrent Neural Network (RNN)
- Global Vectors for Word Representation (GloVe)
- Word2Vec
- Doc2Vec
- Bag-of-Words (scikit-learn: Count Vectorizer)
- Latent Dirichlet Allocation (LDA)
- Autoencoders / Encoder-Decoders
- AI-Powered Search
- Neural Coreference
- 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 Stemming
- 4 Part-of-Speech (POS) Tagging
- 5 Chunking
- 6 Named Entity Recognition (NER)
- 7 Coreference
- 8 Hierarchical Dataless Classifier
- 9 Lemmatization
- 10 Topic Modeling
- 11 Word Embeddings
- 12 Wikifier
- 13 Deep Learning Algorithms
- 14 Summarizer
- 15 Ontologies
- 16 Semantic Role Labeling (SRL)
- 17 Pipeline
- 18 Evaluation Matrics
Regular Expressions (Regex)
Search for text patterns, validate emails and URLs, capture information, and use patterns to save development time.
Tokenization / Sentence Splitting
Stemming
Part-of-Speech (POS) Tagging
Chunking
Named Entity Recognition (NER)
Coreference
Hierarchical Dataless Classifier
Lemmatization
Topic Modeling
Word Embeddings
Wikifier
Deep Learning Algorithms
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.
Pipeline
Evaluation Matrics
Confusion Matrix, Precision, Recall, F Score, ROC Curves, trade off between True Positive Rate and False Positive Rate.
