Sumários

Aplicações de processamento automático de fala

30 Outubro 2020, 16:00 Rita Sousa


Continuação da aula anterior (Fonética acúsctica)

Aplicações

Introdução ao processamento automático de língua falada

28 Outubro 2020, 16:00 Rita Sousa


  • Fonética e processamento de sinal.

Apresentação por um convidado

23 Outubro 2020, 16:00 Rita Sousa


[ Subject ]

STRING, a Hybrid Statistical and Rule-Based Natural Language Processing Chain for Portuguese, has a modular structure and performs all basic text processing tasks, namely:• tokenization and text segmentation,• part-of-speech tagging,• morphosyntactic disambiguation,• shallow parsing (chunking), and• deep parsing (dependency extraction)

[ Biography ]

Nuno Mamede graduated in Electrotechnical and Computers Engineering by the Instituto Superior Técnico (IST), Lisbon, in 1981, and received his MSc and PhD degrees in Electrotechnic and Computers Engineering, from the same University in 1985 and 1992, respectively. In 1982 he started as lecturer and since 2006 he holds a position of Associate Professor in Instituto Superior Técnico, where he has taught Digital Systems, Object Oriented Programming, Programming Languages, knowledge representation, Natural Language Processing. He has been a researcher at INESC-ID Lisboa, in Lisbon, since its creation in 1980. He participated in the foundation of L2F where hold a position in the Executive Board. His activities have been in the areas of Written Natural Language Processing, namely on Syntactic Processing, Named Entity Recognition, and Natural Language Interfaces to Data Bases. He has authored a significant number of scientific papers. He is a member of AAAI, ACM and ACL.

Mini-teste 1

21 Outubro 2020, 16:00 Rita Sousa


  • Realização do primeiro mini-teste.

Resolução de um problema

16 Outubro 2020, 16:00 Rita Sousa


  • Resolução de um problema que exige
  1. o cálculo de probabilidades associada a bigramas;
  2. o cálculo de probabilidades quando se procede a alisamento ( add-one);
  3. o cálculo das contagens equivalentes ao alisamento calculado; e
  4. o cálculo da probabilidade de uma frase usando as probabilidades calculadas anteriormente.