File size: 3,475 Bytes
2374872 6eee871 2374872 19669cc 2374872 7a16091 2374872 7a16091 2374872 6eee871 2374872 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
import gradio as gr
from transformers import pipeline
title = "Automatic Readability Assessment of Texts in Spanish"
description = """
Is a text **complex** or **simple**? Can it be understood by someone learning Spanish with a **basic**, **intermediate** or **advanced** knowledge of the language? Find out with our models below!
"""
article = """
### What's Readability Assessment?
[Automatic Readability Assessment](https://arxiv.org/abs/2105.00973) consists of determining "how difficult" it could be to read and understand a piece of text.
This could be estimated using readability formulas, such as [Flesch for English](https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readability_tests) or [similar ones for Spanish](https://www.siicsalud.com/imagenes/blancopet1.pdf).
However, their dependance on surface statistics (e.g. average sentence length) makes them unreliable.
As such, developing models that could estimate a text's readability by "looking beyond the surface" is a necessity.
### Goal
We aim to contribute to the development of **neural models for readability assessment for Spanish**, following previous work for [English](https://aclanthology.org/2021.cl-1.6/) and [Filipino](https://aclanthology.org/2021.ranlp-1.69/).
### More Information
Details about how we trained these models can be found in our [report](https://wandb.ai/readability-es/readability-es/reports/Texts-Readability-Analysis-for-Spanish--VmlldzoxNzU2MDUx).
### Team
- [Laura Vásquez-Rodríguez](https://lmvasque.github.io/)
- Pedro Cuenca
- Sergio Morales
- [Fernando Alva-Manchego](https://feralvam.github.io/)
"""
examples = [
["Esta es una frase simple.", "simple or complex?"],
["La ciencia nos enseña, en efecto, a someter nuestra razón a la verdad y a conocer y juzgar las cosas como son, es decir, como ellas mismas eligen ser y no como quisiéramos que fueran.", "simple or complex?"],
["Las Líneas de Nazca son una serie de marcas trazadas en el suelo, cuya anchura oscila entre los 40 y los 110 centímetros.", "basic, intermediate, or advanced?"],
["Hace mucho tiempo, en el gran océano que baña las costas del Perú no había peces.", "basic, intermediate, or advanced?"],
["El turismo en Costa Rica es uno de los principales sectores económicos y de más rápido crecimiento del país.", "basic, intermediate, or advanced?"],
]
model_binary = pipeline("sentiment-analysis", model="hackathon-pln-es/readability-es-sentences", return_all_scores=True)
model_ternary = pipeline("sentiment-analysis", model="hackathon-pln-es/readability-es-3class-sentences", return_all_scores=True)
def predict(text, levels):
if levels == 0:
predicted_scores = model_binary(text)[0]
else:
predicted_scores = model_ternary(text)[0]
output_scores = {}
for e in predicted_scores:
output_scores[e['label']] = e['score']
return output_scores
iface = gr.Interface(
fn=predict,
inputs=[
gr.inputs.Textbox(lines=7, placeholder="Write a text in Spanish.", label="Text in Spanish"),
gr.inputs.Radio(choices=["simple or complex?", "basic, intermediate, or advanced?"], type="index", label="Readability Levels"),
],
outputs=[
gr.outputs.Label(num_top_classes=3, label="Predicted Readability Level")
],
theme="huggingface",
title = title, description = description, article = article, examples=examples,
allow_flagging="never",
)
iface.launch() |