Natural Language Processing • NLP Tasks
Named Entity Recognition
- Named entity recognition is the first step towards information extraction that seeks to locate and classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages,etc.
- The task in named entity recognition is to find and classify names in text.
- Named entity recognition (NER) — sometimes referred to as entity chunking, extraction, or identification — is the task of identifying and categorizing key information (entities) in text. An entity can be any word or series of words that consistently refers to the same thing.
- Every detected entity is classified into a predetermined category. For example, an NER machine learning (ML) model might detect the word “super.AI” in a text and classify it as a “Company”.
- It’s a simple NLP task that classifies each word in its context window of neighboring words.
- How does it work?
- NER model is a two step process:
- Detect a named entity
- Categorize the entity
- Use word vectors and make context window of word vectors -> neural network layer -> logistic classifier for specific entity type such as location
- NER model is a two step process:
Dependency Parsing
- Dependency parsing is the task of extracting a dependency parse of a sentence that represents its grammatical structure and defines the relationships between “head” words and words, which modify those heads.
- It is the process of examining the dependencies between the phrases of a sentence in order to determine its grammatical structure.
- A sentence is divided into many sections based mostly on this. The process is based on the assumption that there is a direct relationship between each linguistic unit in a sentence. These hyperlinks are called dependencies.
- A sentence is parsed by choosing for each word what the other word it is dependent of.
- Neural dependency parser(Chen and Manning 2014) takes the main parts of speech tags and dependency labels.
Citation
If you found our work useful, please cite it as:
@article{Chadha2021Distilled,
title = {Neural Nets},
author = {Jain, Vinija and Chadha, Aman},
journal = {Distilled Notes for Stanford CS224n: Natural Language Processing with Deep Learning},
year = {2021},
note = {\url{https://aman.ai}}
}