Tehran Institute for Advanced Studies (TEIAS)

/ Natural Language Processing (undergraduate)

Reading Group

Natural Language Processing (undergraduate)

Undergraduate Study Group

Wednesdays, 10am-11am (online on Skyroom)

Venue

Khatam University
Meeting room, 6th floor, Khatam University (2nd Building) See location on Google map

+982189174612

Organizers

Activities

  • The aim of this study group is to lay the foundations for carrying out research. This includes studying the basics of NLP and Machine Learning (mostly Deep Learning), reading papers, and discussing ideas.

Reading Group

Natural Language Processing (undergraduate)

Previous slide
Next slide

Contact the moderator if you are interested in joining the group.

Current members

Ehsan Aghazade

(UT)

Sepehr Ghaderan

(IUST)

Zahra Hosseini

(IUST)

Mohsen Fayyaz

(UT)

Zhivar Sourati

(IUST)

Alireza Moradi

(IUST)

Parisa Yalsavar

(IUST)

Mahsa Ghaderan

(IUST)

Zahra Bashir

(IUST)

Ghazale Mahmoudi

(IUST)

Sara Kodeiri

(IUST)

Series 1-Summer 2020

Meeting #11

Date

Topic

30 Sep

  • Image captioning: implementing a network to generate captions for input images.

 

Meeting #10

Date

Topic

23 Sep

  • Review of the SQuAD dataset and Question Answering task.
  • Convolutional Neural Networks, a simple classification of MNIST.

Meeting #09

Date

Topic

16 Sep

  • Review of Collobert et al, Natural Language Processing (Almost) from Scratch, 2010.
  • Generative RNN models, Sequence to Sequence architecture. Application to a toy task.

Meeting #08

Date

Topic

02 Sep

Review of two papers:

 

  • P. Turney, From Frequency to Meaning: Vector Space Models of Semantics, 2010.
  • Bolukbasi et al, Man is to Computer Programmer as Woman is to Homemaker, 2016.

Meeting #07

Date

Topic

26 Aug

  • Initiating Farsi NLP tracker, a collection of NLP datasets for Farsi.
  • Imbalanced classification
  • Precision/Recall/F1

 

 

Meeting #06

Date

Topic

19 Aug

  • Optimizers (presentation by Alireza Moradi)
  • NER task for Farsi on Persian-NER
  • TimeDistributed layer in Keras
  • Imbalanced classification
  • Precision/Recall/F1

Meeting #05

Date

Topic

12 Aug

  • Feeding pre-trained embeddings (fastText)
  • Freezing vs. tuning weights
  • More on recurrent neural networks (what is “unit” size?)

 

 

Meeting #04

Date

Topic

29 Jul

  • Understanding the concept of semantic representation: Word embeddings (Word2vec)
  • Implementing a sentiment analysis model on DigiKala data, using LSTMs in Keras

Meeting #03

Date

Topic

22 Jul

 

Meeting #02

Date

Topic

15 Jul

Meeting #01

Date

Topic

8 Jul

Introduction to the study group: aims and objectives.