metadata

language:
  - en
  - zh
tags:
  - GENIUS
  - conditional text generation
  - sketch-based text generation
  - data augmentation
license: apache-2.0
datasets:
  - c4
  - beyond/chinese_clean_passages_80m
widget:
  - text: >-
      <mask> Conference on Empirical Methods <mask> submission of research
      papers <mask> Deep Learning <mask>
    example_title: Example 1
  - text: >-
      <mask> machine learning <mask> my research interest <mask> data science
      <mask>
    example_title: Example 2
  - text: >-
      <mask> play basketball <mask> a strong team <mask> Shanghai University of
      Finance and Economics <mask> last Sunday <mask>
    example_title: Example 3
  - text: >-
      Good news: <mask> the European Union <mask> month by EU <mask> Farm
      Commissioner Franz <mask>
    example_title: Example with a prompt 1
  - text: >-
      Bad news: <mask> the European Union <mask> month by EU <mask> Farm
      Commissioner Franz <mask>
    example_title: Example with a prompt 2
inference:
  parameters:
    max_length: 200
    num_beams: 3
    do_sample: true

💡GENIUS – generating text using sketches!

💡GENIUS is a powerful conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated by mask tokens). GENIUS is pre-trained on a large-scale textual corpus with a novel reconstruction from sketch objective using an extreme and selective masking strategy, enabling it to generate diverse and high-quality texts given sketches.

GENIUS can also be used as a general textual data augmentation tool for various NLP tasks (including sentiment analysis, topic classification, NER, and QA).

Models hosted in 🤗 Huggingface:

Model variations:

Model	#params	Language	comment
`genius-large`	406M	English	The version used in paper (recommend)
`genius-large-k2t`	406M	English	keywords-to-text
`genius-base`	139M	English	smaller version
`genius-base-ps`	139M	English	pre-trained both in paragraphs and short sentences
`genius-base-chinese`	116M	中文	在一千万纯净中文段落上预训练

Usage

What is a sketch?

First, what is a sketch? As defined in our paper, a sketch is "key information consisting of textual spans, phrases, or words, concatenated by mask tokens". It's like a draft or framework when you begin to write an article. With GENIUS model, you can input some key elements you want to mention in your wrinting, then the GENIUS model can generate cohrent text based on your sketch.

The sketch which can be composed of:

keywords /key-phrases, like __NLP__AI__computer__science__
spans, like Conference on Empirical Methods__submission of research papers__
sentences, like I really like machine learning__I work at Google since last year__
or a mixup!

(the __ is the mask token. Use <mask> for English, and [MASK] for Chinese)

How to use the model

1. If you already have a sketch in mind, and want to get a paragraph based on it...

from transformers import pipeline
# 1. load the model with the huggingface `pipeline`
genius = pipeline("text2text-generation", model='beyond/genius-large', device=0)
# 2. provide a sketch (joint by <mask> tokens)
sketch = "<mask> Conference on Empirical Methods <mask> submission of research papers <mask> Deep Learning <mask>"
# 3. here we go!
generated_text = genius(sketch, num_beams=3, do_sample=True, max_length=200)[0]['generated_text']
print(generated_text)

Output:

'The Conference on Empirical Methods welcomes the submission of research papers. Abstracts should be in the form of a paper or presentation. Please submit abstracts to the following email address: eemml.stanford.edu. The conference will be held at Stanford University on April 1618, 2019. The theme of the conference is Deep Learning.'

If you have a lot of sketches, you can batch-up your sketches to a Huggingface Dataset object, which can be much faster.

TODO: we are also building a python package for more convenient use of GENIUS, which will be released in few weeks.

2. If you have an NLP dataset (e.g. classification) and want to do data augmentation to enlarge your dataset...

Please check genius/augmentation_clf and genius/augmentation_ner_qa, where we provide ready-to-run scripts for data augmentation for text classification/NER/MRC tasks.