Skip to content

Latest commit

 

History

History
54 lines (47 loc) · 3.52 KB

Activity-Log.md

File metadata and controls

54 lines (47 loc) · 3.52 KB

Dataset

  • Large Movie Review Dataset
  • Source: using torchtext imdb implementation
  • Downsampled to 2500 examples - training and validation 1250 each.

Related Works

Adversarial Learning

Adversarial Learning for NLP

Model for Sentiment Analysis

Experiment

  • Naive Bayes
  • CNN
  • Bidirectional RNN
  • Bidirectional LSTM

Evaluation

Classifier Evaluation

  • Accuracy, precision, recall
  • Loss function analysis
    • Increment of loss
    • Change of classifier confidence (probability) (i.e. sigmoid output)

Adversarial Example Evaluation

  • Imperceptibility analysis
    • Human evaluation
    • Quantitative measurement: thought vectors
  • Sentence error analysis
    • Syntactic error: word replacement incur grammatical error
    • Semantic error: meaning of the sentence change after word replacement
    • Counterfactual error: some fact in the sentence is incorrect after word replacement

TODO - Midterm Report

  • Research question, data collection, related work (adversarial learning), Experiment (@Erica)
  • Related work (adversarial learning for NLP x5), Experiment (@Alicia)
  • Related work (adversarial learning for NLP x3), Evaluation, Experiment, Future work (@Tobey)