DElIteraTeR-RoBERTa-Intent-Span-Detector

This model was obtained by fine-tuning roberta-large on IteraTeR+ multi_sent dataset.

Paper: Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks
Authors: Zae Myung Kim, Wanyu Du, Vipul Raheja, Dhruv Kumar, and Dongyeop Kang

Usage

import torch
from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("zaemyung/DElIteraTeR-RoBERTa-Intent-Span-Detector")

# update tokenizer with special tokens
INTENT_CLASSES = ['none', 'clarity', 'fluency', 'coherence', 'style', 'meaning-changed']  # `meaning-changed` is not used
INTENT_OPENED_TAGS = [f'<{intent_class}>' for intent_class in INTENT_CLASSES]
INTENT_CLOSED_TAGS = [f'</{intent_class}>' for intent_class in INTENT_CLASSES]
INTENT_TAGS = set(INTENT_OPENED_TAGS + INTENT_CLOSED_TAGS)
special_tokens_dict = {'additional_special_tokens': ['<bos>', '<eos>'] + list(INTENT_TAGS)}
tokenizer.add_special_tokens(special_tokens_dict)

model = AutoModelForTokenClassification.from_pretrained("zaemyung/DElIteraTeR-RoBERTa-Intent-Span-Detector")

id2label = {0: "none", 1: "clarity", 2: "fluency", 3: "coherence", 4: "style", 5: "meaning-changed"}

before_text = '<bos>I likes coffee?<eos>'
model_input = tokenizer(before_text, return_tensors='pt')
model_output = model(**model_input)
softmax_scores = torch.softmax(model_output.logits, dim=-1)
pred_ids = torch.argmax(softmax_scores, axis=-1)[0].tolist()
pred_intents = [id2label[_id] for _id in pred_ids]

tokens = tokenizer.convert_ids_to_tokens(model_input['input_ids'][0])

for token, pred_intent in zip(tokens, pred_intents):
    print(f"{token}: {pred_intent}")

"""
<s>: none
<bos>: none
I: fluency
Ġlikes: fluency
Ġcoffee: none
?: none
<eos>: none
</s>: none
"""