movie-roberta-squad / README.md
thatdramebaazguy's picture
Update README.md
00d41ff
metadata
datasets:
  - imdb
  - cornell_movie_dialogue
  - SQuAD
language:
  - English
thumbnail: null
tags:
  - roberta
  - roberta-base
  - question-answering
  - qa
  - movies
license: cc-by-4.0

roberta-base + DAPT + Domain-Specific QA

Objective: This is Roberta Base with Domain Adaptive Pretraining on Movie Corpora --> Then a changed head to do the SQuAD Task. This makes a QA model capable of answering questions in the movie domain.
https://huggingface.co/thatdramebaazguy/movie-roberta-base was used as the MovieRoberta.

model_name = "thatdramebaazguy/movie-roberta-squad"
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="question-answering")

Overview

Language model: roberta-base
Language: English
Downstream-task: QA
Training data: imdb, polarity movie data, cornell_movie_dialogue, 25mlens movie names, SQuADv1
Eval data: MoviesQA (From https://github.com/ibm-aur-nlp/domain-specific-QA)
Infrastructure: 1x Tesla v100
Code: See example

Hyperparameters

Num examples = 88567  
Num Epochs = 10
Instantaneous batch size per device = 32  
Total train batch size (w. parallel, distributed & accumulation) = 32  

Performance

Eval on MoviesQA

  • eval_samples = 5032
  • exact_match = 51.64944
  • f1 = 65.53983

Eval on SQuADv1

  • exact_match = 81.23936
  • f1 = 89.27827

Github Repo: