Simple-QE: Better Automatic Quality Estimation for Text Simplification

12/22/2020
by   Reno Kriz, et al.
0

Text simplification systems generate versions of texts that are easier to understand for a broader audience. The quality of simplified texts is generally estimated using metrics that compare to human references, which can be difficult to obtain. We propose Simple-QE, a BERT-based quality estimation (QE) model adapted from prior summarization QE work, and show that it correlates well with human quality judgments. Simple-QE does not require human references, which makes the model useful in a practical setting where users would need to be informed about the quality of generated simplifications. We also show that we can adapt this approach to accurately predict the complexity of human-written texts.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

09/02/2019

SumQE: a BERT-based Summary Quality Estimation Model

We propose SumQE, a novel Quality Estimation model for summarization bas...
06/03/2019

Handling Divergent Reference Texts when Evaluating Table-to-Text Generation

Automatically constructed datasets for generating text from semi-structu...
10/06/2017

A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification

Text summarization and text simplification are two major ways to simplif...
10/20/2020

Human-Paraphrased References Improve Neural Machine Translation

Automatic evaluation comparing candidate translations to human-generated...
06/10/2019

Detecting Everyday Scenarios in Narrative Texts

Script knowledge consists of detailed information on everyday activities...
10/20/2020

AutoMeTS: The Autocomplete for Medical Text Simplification

The goal of text simplification (TS) is to transform difficult text into...
07/02/2017

Automatic Trimap Generation for Image Matting

Image matting is a longstanding problem in computational photography. Al...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.