Skip to content

Latest commit

 

History

History
70 lines (47 loc) · 5.7 KB

README.md

File metadata and controls

70 lines (47 loc) · 5.7 KB

English Version

Processamento de Linguagem Natural

Este é um conjunto de palestras e materiais sobre processamento de linguagem natural, provendo uma introdução aos princiais métodos e algoritmos usados no tratamento de problemas envolvendo linguagem natural. Veja também os cursos atuais relacionados a esse tópico:

Introdução

Processamento de Linguagem Natural, ou NLP do acrôniônimo em ingês para Natural Language Processing, é uma das mais importantes tecnologias atualmente, uma vez que pessoas se comunicam predominantemente usando linguagens, de email, mensagens instantâneas, busca na Web e postagens em redes sociais à serviços ao consumidor e relatórios médicos. Particularmente, NLP refere-se ao conjunto de métodos que tornam linguagem humana acessível à máquinas [2]. O termo designa o projeto e análise de representações, métodos e algoritmos para tratamento de problemas práticos de linguagem, tomando como entrada ou produzindo como saída dados não estruturados em linguagem natural humana [3]. Geralmente, problemas em NLP envolvem reconhecimento automático de fala (automatic speech recognition), sumariza&ccedilão de textos (text summarization), extração de informação (information extraction), tradução automática (machine translation), gera&ccedilão e compreesão de linguagem natural (natural language understanding and generation), análise de discurso e de sentimento (sentiment and discouse analysis).

The history of NLP dates back to the 1950s with experiments on automatic machine translation [6]. In the following years experiments on chatbots, conceptual ontologies and question answering were developed and the proposed approaches were mostly based on complex sets of hand-written rules. In the late 80's, the introduction of machine learning algorithms for language processing produced a new paradigm distinct from rule-based NLP, with research mostly focusing on the development of statistical models to make probabilistic decisions based on features extracted from text corpus [5].

Recent advances in artificial intelligence and high performance computing have led to an intensive use of new machine learning models powering NLP applications. In particular, deep neural network based approaches have obtained very high performance across many different NLP tasks [4]. These models can often be trained with a single end-to-end model and do not require traditional, task specific feature engineering. Such neural NLP have been they have been more effective for understanding complex language utterances and have been viewed as a new paradigm distinct from statistical NLP.

Palestras

  1. Introduction to NLP [ slides ]
  2. Vector representations [ slides ]
  3. Language modeling [ slides ]
  4. Text classification [ slides ]
  5. Linear models for NLP [ slides ]
  6. Introduction to neural networks [ slides ]
  7. Tagging [ slides ]
  8. Sequence labeling [ slides ]
  9. Language generation [ slides ]
  10. Parsing and context-free grammars [ slides ]
  11. Text embeddings [ slides ]
  12. Neural language models [ slides ]

Material

Videos

  1. Channel: Natural Language Processing with Deep Learning by Stanford University.

Outros Recursos

  1. Neural Networks and Deep Learning by Michael A. Nielsen.
  2. Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville.

Informação Adicional

Most of the topics of the lectures are taken from [1], [2] and [3]. Material and assignments are mostly inspired by the Stanford course Natural Language Processing with Deep Learning.

Referências

[1] Dan Jurafsky, and James H. Martin. Speech and Language Processing. 3rd ed. 2019.

[2] Jacob Eisenstein. Natural Language Processing. MIT Press. 2018.

[3] Yoav Goldberg. Neural network methods for natural language processing. Synthesis Lectures on Human Language Technologies, 10(1):1–309. 2017.

[4] Yoav Goldberg. A Primer on Neural Network Models for Natural Language Processing. Journal of Artificial Intelligence Research, 57(1):345-420. 2016.

[5] Mark Johnson. How the Statistical Revolution Changes (Computational) Linguistics. In Proceedings of the EACL Workshop on the Interaction between Linguistics and Computational Linguistics, p. 3-11, 2009.

[6] Conference on Mechanical Translation. MIT. 1952.