Difference between revisions of "Natural Language Processing (NLP)"
(→NLP Pipeline) |
|||
| Line 128: | Line 128: | ||
<youtube>VrT3TRDDE4M</youtube> | <youtube>VrT3TRDDE4M</youtube> | ||
| − | == | + | == Ontologies == |
| + | [http://www.youtube.com/results?search_query=Ontologies+Ontology+taxonomy+nlp+natural+language Youtube search...] | ||
| + | |||
| + | (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. | ||
| + | |||
| + | <youtube>WayalrOkCkY</youtube> | ||
| + | <youtube>k5X12mdEvb8</youtube> | ||
| + | |||
| + | == Pipeline == | ||
[http://www.youtube.com/results?search_query=Pipeline+workflow+workbench+nlp+natural+language Youtube search...] | [http://www.youtube.com/results?search_query=Pipeline+workflow+workbench+nlp+natural+language Youtube search...] | ||
* [https://github.com/CogComp/cogcomp-nlp/tree/master/pipeline CogComp NLP Pipeline | Cognitive Computation Group, led by Prof. Dan Roth] | * [https://github.com/CogComp/cogcomp-nlp/tree/master/pipeline CogComp NLP Pipeline | Cognitive Computation Group, led by Prof. Dan Roth] | ||
| − | <youtube> | + | <youtube>k5X12mdEvb8</youtube> |
| + | <youtube>k5X12mdEvb8</youtube> | ||
== [[Evaluation Matrics]] == | == [[Evaluation Matrics]] == | ||
Revision as of 10:37, 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)
- 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 Semantic Role Labeling (SRL)
- 9 Hierarchical Dataless Classifier
- 10 Lemmatization
- 11 Topic Modeling
- 12 Word Embeddings
- 13 Deep Learning Algorithms
- 14 Summarizer
- 15 Wikifier
- 16 Ontologies
- 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
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.
Hierarchical Dataless Classifier
Lemmatization
Topic Modeling
Word Embeddings
Deep Learning Algorithms
Summarizer
Wikifier
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.
Pipeline
Evaluation Matrics
Confusion Matrix, Precision, Recall, F Score, ROC Curves, trade off between True Positive Rate and False Positive Rate.
