Edit model card

IteraTeR BART model

This model was obtained by fine-tuning facebook/bart-base on IteraTeR-full-sent dataset.

Paper: Understanding Iterative Revision from Human-Written Text
Authors: Wanyu Du, Vipul Raheja, Dhruv Kumar, Zae Myung Kim, Melissa Lopez, Dongyeop Kang

Text Revision Task

Given an edit intention and an original sentence, our model can generate a revised sentence.
The edit intentions are provided by IteraTeR-full-sent dataset, which are categorized as follows:

Edit Intention Definition Example
clarity Make the text more formal, concise, readable and understandable. Original: It's like a house which anyone can enter in it.
Revised: It's like a house which anyone can enter.
fluency Fix grammatical errors in the text. Original: In the same year he became the Fellow of the Royal Society.
Revised: In the same year, he became the Fellow of the Royal Society.
coherence Make the text more cohesive, logically linked and consistent as a whole. Original: Achievements and awards Among his other activities, he founded the Karachi Film Guild and Pakistan Film and TV Academy.
Revised: Among his other activities, he founded the Karachi Film Guild and Pakistan Film and TV Academy.
style Convey the writer’s writing preferences, including emotions, tone, voice, etc.. Original: She was last seen on 2005-10-22.
Revised: She was last seen on October 22, 2005.

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("wanyu/IteraTeR-BART-Revision-Generator")
model = AutoModelForSeq2SeqLM.from_pretrained("wanyu/IteraTeR-BART-Revision-Generator")
before_input = '<fluency> I likes coffee.'
model_input = tokenizer(before_input, return_tensors='pt')
model_outputs = model.generate(**model_input, num_beams=8, max_length=1024)
after_text = tokenizer.batch_decode(model_outputs, skip_special_tokens=True)[0]
Downloads last month
9
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.