There are 1 repository under text-simplification topic.
A Natural Portuguese Language Benchmark (Napolab) for the evaluation of language models.
MILES is a multilingual text simplifier inspired by LSBert - A BERT-based lexical simplification approach proposed in 2018. Unlike LSBert, MILES uses the bert-base-multilingual-uncased model, as well as simple language-agnostic approaches to complex word identification (CWI) and candidate ranking.
Codebase, data and models for the Keep it Simple paper at ACL2021
An implementation of transformer-based language model for sentence rewriting tasks such as summarization, simplification, and grammatical error correction.
Text simplification for a better world: Deep-Martin Transformer 🤗
Dataset containing scroll interactions of 598 partcipants reading advanced and elementary texts from the OneStopEnglish corpus
Klexikon: A German Dataset for Joint Summarization and Simplification
Annotation Tool for Text Simplification Corpora
An unsupervised approach to sentence simplification that combines text generation and text revision.
Sentence-Level Text Simplification for Dutch
A collection of tools for sentence alignement
This is the reimplementation of the NeuralTextSimplification system in Pytorch.
Hebrew Text Simplification system based on LLMs & advanced algorithms, served as a Chrome plugin.
Success and Failure Linguistic Simplification Annotation 💃
Meta-evaluation of automatic metrics in Text Simplification
InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification
TSAR2022 Shared Task on Lexical Simplification - uniHD entry
Code and data for discourse-based sentence splitting experiments.
Deploying and monitoring an mBART model (trained for text simplification), on Kubernetes or Docker
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
Source code for Text Simplification Evaluation papers at ACL findings and CTTS workshop.
Data collection for a German Simplification Corpus. Later on an overvoew of all requested websites will be added. Furthermore, the license, the code for craling and aligning will be added.
Reference-less Quality Estimation of Text Simplification Systems
the code and resources for multi-level complexity-controllable MT
Wikipedia-Vikidia Corpus (WiViCo) - A general-purpose parallel sentence simplification dataset for French
Dataset with manual simplifications of COVID-19 information in English and Spanish.
Medical Text Simplification Project for a Special Topics in Natural Language Processing class
A bunch of experiments to improve text simplification (TS) tasks using encoder-decoder transformers