ComVE-distilgpt2 /
language: "en"
- exbert
- commonsense
- semeval2020
- comve
license: "mit"
- ComVE
- bleu
- text: "Chicken can swim in water. <|continue|>"
# ComVE-distilgpt2
## Model description
Finetuned model on Commonsense Validation and Explanation (ComVE) dataset introduced in [SemEval2020 Task4]( using a causal language modeling (CLM) objective.
The model is able to generate a reason why a given natural language statement is against commonsense.
## Intended uses & limitations
You can use the raw model for text generation to generate reasons why natural language statements are against commonsense.
#### How to use
You can use this model directly to generate reasons why the given statement is against commonsense using [``]( script.
*Note:* make sure that you are using version `2.4.1` of `transformers` package. Newer versions has some issue in text generation and the model repeats the last token generated again and again.
#### Limitations and bias
The model biased to negate the entered sentence usually instead of producing a factual reason.
## Training data
The model is initialized from the [distilgpt2]( model and finetuned using [ComVE]( dataset which contains 10K against commonsense sentences, each of them is paired with three reference reasons.
## Training procedure
Each natural language statement that against commonsense is concatenated with its reference reason with `<|continue|>` as a separator, then the model finetuned using CLM objective.
The model trained on Nvidia Tesla P100 GPU from Google Colab platform with 5e-5 learning rate, 15 epochs, 128 maximum sequence length and 64 batch size.
<img src="">
## Eval results
The model achieved 13.7582/13.8026 BLEU scores on SemEval2020 Task4: Commonsense Validation and Explanation development and testing dataset.
### BibTeX entry and citation info
title={JUSTers at SemEval-2020 Task 4: Evaluating Transformer Models Against Commonsense Validation and Explanation},
author={Fadel, Ali and Al-Ayyoub, Mahmoud and Cambria, Erik},
<a href="">
<img width="300px" src="">