SOTAVerified

Text Simplification

Text Simplification is the task of reducing the complexity of the vocabulary and sentence structure of text while retaining its original meaning, with the goal of improving readability and understanding. Simplification has a variety of important societal applications, for example increasing accessibility for those with cognitive disabilities such as aphasia, dyslexia, and autism, or for non-native speakers and children with reading difficulties.

Source: Multilingual Unsupervised Sentence Simplification

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 468 papers

TitleStatusHype
Traditional Readability Formulas Compared for English—0
TextBox 2.0: A Text Generation Library with Pre-trained Language ModelsCode3
Automatic Text Simplification of News Articles in the Context of Public Broadcasting—0
MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders—0
(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification—0
LENS: A Learnable Evaluation Metric for Text SimplificationCode1
Patient-friendly Clinical Notes: Towards a new Text Simplification DatasetCode0
Improving Iterative Text Revision by Learning Where to Edit from Other Revision TasksCode1
Cognitive Simplification Operations Improve Text SimplificationCode0
Noisy Channel for Automatic Text Simplification—0
Is Character Trigram Overlapping Ratio Still the Best Similarity Measure for Aligning Sentences in a Paraphrased Corpus?—0
CEFR-Based Sentence Difficulty Annotation and AssessmentCode1
Arabic Word-level Readability Visualization for Assisted Text Simplification—0
Shallow Discourse Parsing for Open Information Extraction and Text Simplification—0
Text Simplification of College Admissions Instructions: A Professionally Simplified and Verified Corpus—0
Unsupervised Simplification of Legal Texts—0
Pseudo-Labels Are All You Need—0
Sequence to sequence pretraining for a less-resourced Slovenian languageCode0
Complex Word Identification in Vietnamese: Towards Vietnamese Text Simplification—0
An Evaluation of Binary Comparative Lexical Complexity Models—0
Unsupervised Sentence Simplification via Dependency ParsingCode0
Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in RussianCode1
A Multilingual Simplified Language News Corpus—0
Open corpora and toolkit for assessing text readability in FrenchCode0
The Swedish Simplification Toolkit: – Designed with Target Audiences in Mind—0
CWID-hi: A Dataset for Complex Word Identification in Hindi Text—0
HECTOR: A Hybrid TExt SimplifiCation TOol for Raw Texts in French—0
Evaluation of Automatic Text Simplification: Where are we now, where should we go from here—0
Towards Readability-Controlled Machine Translation of COVID-19 Texts—0
MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification—0
Lossless Acceleration for Seq2seq Generation with Aggressive DecodingCode0
Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identification—0
One Size Does Not Fit All: The Case for Personalised Word Complexity Models—0
Predicting Sentence Deletions for Text Simplification Using a Functional Discourse Structure—0
TS-ANNO: An Annotation Tool to Build, Annotate and Evaluate Text Simplification CorporaCode1
On the Ethical Considerations of Text Simplification—0
SimpleBERT: A Pre-trained Model That Learns to Generate Simple Words—0
Text Revision by On-the-Fly Representation OptimizationCode0
Evaluating Factuality in Text SimplificationCode0
Learning to Simplify with Data Hopelessly Out of Alignment—0
An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models—0
Klexikon: A German Dataset for Joint Summarization and SimplificationCode1
Unsupervised Sentence Simplification via Dependency Parsing—0
The Common Readability Formula & Five Adjusted Readability Formulas for Text Simplification, Medical Documents and Other General Uses—0
Automatic Lexical Simplification for Turkish—0
Towards more patient friendly clinical notes through language models and ontologies—0
The (Un)Suitability of Automatic Evaluation Metrics for Text SimplificationCode0
Combining Paraphrase Pre-trained Model and Controllable Rules for Unsupervised Sentence Simplification—0
Divide-and-Conquer Text Simplification by Scalable Data Enhancement—0
Few-shot Controllable Style Transfer for Low-Resource Multilinugal Settings—0
Show:102550
← PrevPage 3 of 10Next →
All datasetsTurkCorpusASSETNewselaPWKP / WikiSmallDEplain-APA-docDEplain-web-docEurekaAlertDEplain-APA-sentDEplain-web-sentWikiLargeFRWiki-Auto + Turk

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-175B (6 SARI-selected examples, high/low)SARI (EASSE>=0.2.1)43.46—Unverified
2MUSS (BART+ACCESS Supervised)SARI (EASSE>=0.2.1)42.53—Unverified
3Control Prefixes (BART)SARI (EASSE>=0.2.1)42.32—Unverified
4TSTSARI (EASSE>=0.2.1)41.46—Unverified
5ACCESSSARI (EASSE>=0.2.1)41.38—Unverified
6MUSS (BART+ACCESS Unsupervised)SARI (EASSE>=0.2.1)40.85—Unverified
7DMASS-DCSSSARI (EASSE>=0.2.1)40.45—Unverified
8SBMT-SARISARI (EASSE>=0.2.1)39.56—Unverified
9EditNTSSARI (EASSE>=0.2.1)38.22—Unverified
10PBMT-RSARI (EASSE>=0.2.1)38.04—Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-175B (15 SARI-selected examples, random ordering)BLEU73.92—Unverified
2MUSS (BART+ACCESS Supervised)BLEU72.98—Unverified
3Control Prefixes (BART)SARI (EASSE>=0.2.1)43.58—Unverified
4TSTSARI (EASSE>=0.2.1)43.21—Unverified
5MUSS (BART+ACCESS Unsupervised)SARI (EASSE>=0.2.1)42.65—Unverified
6ACCESSSARI (EASSE>=0.2.1)40.13—Unverified
7DMASS-DCSSSARI (EASSE>=0.2.1)38.67—Unverified
8Dress-LSSARI (EASSE>=0.2.1)36.59—Unverified
9UNTS (Unsupervised)SARI (EASSE>=0.2.1)35.19—Unverified
10PBMT-RSARI (EASSE>=0.2.1)34.63—Unverified
#ModelMetricClaimedVerifiedStatus
1CRF Alignment + TransformerSARI36.6—Unverified
2Pointer + Multi-task Entailment and Paraphrase GenerationSARI33.22—Unverified
3EditNTSSARI31.41—Unverified
4S2S-Cluster-FASARI30.73—Unverified
5Edit-Unsup-TSSARI30.44—Unverified
6NSELSTM-SSARI29.58—Unverified
7NSELSTM-BSARI27.42—Unverified
8DRESSSARI27.37—Unverified
9DMASS + DCSSSARI27.28—Unverified
10DRESS-LSSARI26.63—Unverified
#ModelMetricClaimedVerifiedStatus
1NSELSTM-BBLEU53.42—Unverified
2TSTSARI44.67—Unverified
3UNSUPBLEU38.47—Unverified
4DRESS-LSBLEU36.32—Unverified
5DRESSBLEU34.53—Unverified
6EditNTSSARI32.35—Unverified
7NSELSTM-SBLEU29.72—Unverified
8Pointer + Multi-task Entailment and Paraphrase GenerationBLEU27.23—Unverified
#ModelMetricClaimedVerifiedStatus
1long-mBART (trained on DEplain-APA-doc)SARI (EASSE>=0.2.1)44.56—Unverified
2long-mBART (trained on DEplain-APA-doc & DEplain-web-doc)SARI (EASSE>=0.2.1)42.86—Unverified
3long-mBART (trained on DEplain-web-doc)SARI (EASSE>=0.2.1)35.02—Unverified
#ModelMetricClaimedVerifiedStatus
1long-mBART (trained on DEplain-APA-doc & DEplain-web-doc)SARI (EASSE>=0.2.1)49.75—Unverified
2long-mBART (trained on DEplain-web-doc)SARI (EASSE>=0.2.1)49.58—Unverified
3long-mBART (trained on DEplain-APA-doc)SARI (EASSE>=0.2.1)43.09—Unverified
#ModelMetricClaimedVerifiedStatus
1SATSSARI40.83—Unverified
2MedTSS-BART (Without Training)Rouge135.17—Unverified
3HTSSRouge121.94—Unverified
#ModelMetricClaimedVerifiedStatus
1mBART (trained on DEplain-APA-sent & DEplain-web-sent)SARI (EASSE>=0.2.1)34.9—Unverified
2mBART (trained on DEplain-APA-sent)SARI (EASSE>=0.2.1)34.82—Unverified
#ModelMetricClaimedVerifiedStatus
1mBART (trained on DEplain-APA-sent & DEplain-web-sent)SARI (EASSE>=0.2.1)34.83—Unverified
2mBART (trained on DEplain-APA-sent)SARI (EASSE>=0.2.1)30.87—Unverified
#ModelMetricClaimedVerifiedStatus
1mT5 (fine-tuned on MULTI-SIM)SARI39.23—Unverified
2LSTMSARI39.05—Unverified
#ModelMetricClaimedVerifiedStatus
1BART (TextBox 2.0)BLEU-490.81—Unverified