This is Roberta Base with Domain Adaptive Pretraining on Movie Corpora --> Then trained for the NER task using MIT Movie Dataset --> Then a changed head to do the SQuAD Task. This makes a QA model capable of answering questions in the movie domain, with additional information coming from a different task (NER - Task Transfer). 
https://huggingface.co/thatdramebaazguy/movie-roberta-base was used as the MovieRoberta.

---
datasets:
- imdb (Movie corpus for Domain Adaptive Pretraining)
- cornell_movie_dialogue 
- MIT Movie (NER Dataset)

language: 
- English

thumbnail: 

tags:
- roberta
- roberta-base
- question-answering
- qa
- movies

license: cc-by-4.0

---
# roberta-base for MLM 

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

## Overview
**Language model:** roberta-base  
**Language:** English  
**Downstream-task:** NER --> QA  
**Training data:** imdb, polarity movie data, cornell_movie_dialogue, 25mlens movie names, MIT Movie, SQuADv1
**Eval data:** MoviesQA (From https://github.com/ibm-aur-nlp/domain-specific-QA) 
**Infrastructure**: 4x Tesla v100   
**Code:**  See [example](https://github.com/adityaarunsinghal/Domain-Adaptation/blob/master/scripts/shell_scripts/movieR_NER_squad.sh)    

## Hyperparameters
```
Num examples = 88567
Num Epochs = 3
Instantaneous batch size per device = 32
Total train batch size (w. parallel, distributed & accumulation) = 128
Gradient Accumulation steps = 1
Total optimization steps = 119182
eval_loss  = 1.6153
eval_samples = 20573
perplexity = 5.0296
learning_rate=5e-05
n_gpu = 4

``` 
## Performance

### Eval on MoviesQA
eval_samples =   10790
2021-05-07 21:48:01,204 >>   exact_match  = 83.0274
2021-05-07 21:48:01,204 >>   f1           = 90.1615

Github Repo: 
- [Domain-Adaptation Project](https://github.com/adityaarunsinghal/Domain-Adaptation/)

---