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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 176–200 of 468 papers

Title	Date	Tasks	Status
A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification	Aug 1, 2021	Text Simplification	—Unverified
Automatic Sentence Simplification in Low Resource Settings for Urdu	Aug 1, 2021	SentenceText Simplification	—Unverified
Investigating Text Simplification Evaluation	Jul 28, 2021	Text Simplification	CodeCode Available
What Makes a Concept Complex? Measuring Conceptual Complexity as a Precursor for Text Simplification	Jul 1, 2021	Binary ClassificationLexical Simplification	—Unverified
Parallel Text Alignment and Monolingual Parallel Corpus Creation from Philosophical Texts for Text Simplification	Jun 1, 2021	Text Simplification	CodeCode Available
Improving Human Text Simplification with Sentence Fusion	Jun 1, 2021	RerankingSentence	—Unverified
Simplification automatique de textes biomédicaux en français: lorsque des données précises de petite taille aident (French Biomedical Text Simplification : When Small and Precise Helps )	Jun 1, 2021	Text Simplification	—Unverified
Creating an Aligned Russian Text Simplification Dataset from Language Learner Data	Apr 1, 2021	Text Simplification	—Unverified
Finding Spoiler Bias in Tweets by Zero-shot Learning and Knowledge Distilling from Neural Text Simplification	Apr 1, 2021	Split and RephraseText Simplification	CodeCode Available
Predicting Lexical Complexity in English Texts: The Complex 2.0 Dataset	Feb 17, 2021	Complex Word IdentificationLexical Complexity Prediction	—Unverified
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics	Feb 2, 2021	Abstractive Text SummarizationCross-Lingual Abstractive Summarization	—Unverified
Simple-QE: Better Automatic Quality Estimation for Text Simplification	Dec 22, 2020	Text Simplification	—Unverified
CUT: Controllable Unsupervised Text Simplification	Dec 3, 2020	Text SimplificationTranslation	—Unverified
SEMA: Text Simplification Evaluation through Semantic Alignment	Dec 1, 2020	Text Simplification	—Unverified
French Biomedical Text Simplification: When Small and Precise Helps	Dec 1, 2020	Text Simplification	—Unverified
On the Helpfulness of Document Context to Sentence Simplification	Dec 1, 2020	SentenceText Simplification	CodeCode Available
Leveraging Contextual Embeddings and Idiom Principle for Detecting Idiomaticity in Potentially Idiomatic Expressions	Dec 1, 2020	Text SimplificationWord Embeddings	—Unverified
Semantic Structural Decomposition for Neural Machine Translation	Dec 1, 2020	Machine TranslationSemantic Parsing	CodeCode Available
Text Simplification with Reinforcement Learning Using Supervised Rewards on Grammaticality, Meaning Preservation, and Simplicity	Dec 1, 2020	reinforcement-learningReinforcement Learning	—Unverified
Context-Aware Automatic Text Simplification of Health Materials in Low-Resource Domains	Nov 1, 2020	Text Simplification	—Unverified
Controllable Text Simplification with Explicit Paraphrasing	Oct 21, 2020	Data AugmentationText Simplification	—Unverified
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification	Oct 20, 2020	Explanation GenerationSentence	CodeCode Available
Seq2Edits: Sequence Transduction Using Span-level Edit Operations	Sep 23, 2020	Grammatical Error CorrectionSentence	CodeCode Available
Small but Mighty: New Benchmarks for Split and Rephrase	Sep 17, 2020	SentenceSplit and Rephrase	—Unverified
A Survey on Text Simplification	Aug 19, 2020	Semantic SimilaritySemantic Textual Similarity	—Unverified

Show:10 25 50

← PrevPage 8 of 19Next →

All datasets TurkCorpus ASSET Newsela PWKP / WikiSmall DEplain-APA-doc DEplain-web-doc EurekaAlert DEplain-APA-sent DEplain-web-sent WikiLargeFR Wiki-Auto + Turk

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	GPT-175B (6 SARI-selected examples, high/low)	SARI (EASSE>=0.2.1)	43.46	—	Unverified
2	MUSS (BART+ACCESS Supervised)	SARI (EASSE>=0.2.1)	42.53	—	Unverified
3	Control Prefixes (BART)	SARI (EASSE>=0.2.1)	42.32	—	Unverified
4	TST	SARI (EASSE>=0.2.1)	41.46	—	Unverified
5	ACCESS	SARI (EASSE>=0.2.1)	41.38	—	Unverified
6	MUSS (BART+ACCESS Unsupervised)	SARI (EASSE>=0.2.1)	40.85	—	Unverified
7	DMASS-DCSS	SARI (EASSE>=0.2.1)	40.45	—	Unverified
8	SBMT-SARI	SARI (EASSE>=0.2.1)	39.56	—	Unverified
9	EditNTS	SARI (EASSE>=0.2.1)	38.22	—	Unverified
10	PBMT-R	SARI (EASSE>=0.2.1)	38.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT-175B (15 SARI-selected examples, random ordering)	BLEU	73.92	—	Unverified
2	MUSS (BART+ACCESS Supervised)	BLEU	72.98	—	Unverified
3	Control Prefixes (BART)	SARI (EASSE>=0.2.1)	43.58	—	Unverified
4	TST	SARI (EASSE>=0.2.1)	43.21	—	Unverified
5	MUSS (BART+ACCESS Unsupervised)	SARI (EASSE>=0.2.1)	42.65	—	Unverified
6	ACCESS	SARI (EASSE>=0.2.1)	40.13	—	Unverified
7	DMASS-DCSS	SARI (EASSE>=0.2.1)	38.67	—	Unverified
8	Dress-LS	SARI (EASSE>=0.2.1)	36.59	—	Unverified
9	UNTS (Unsupervised)	SARI (EASSE>=0.2.1)	35.19	—	Unverified
10	PBMT-R	SARI (EASSE>=0.2.1)	34.63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CRF Alignment + Transformer	SARI	36.6	—	Unverified
2	Pointer + Multi-task Entailment and Paraphrase Generation	SARI	33.22	—	Unverified
3	EditNTS	SARI	31.41	—	Unverified
4	S2S-Cluster-FA	SARI	30.73	—	Unverified
5	Edit-Unsup-TS	SARI	30.44	—	Unverified
6	NSELSTM-S	SARI	29.58	—	Unverified
7	NSELSTM-B	SARI	27.42	—	Unverified
8	DRESS	SARI	27.37	—	Unverified
9	DMASS + DCSS	SARI	27.28	—	Unverified
10	DRESS-LS	SARI	26.63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	NSELSTM-B	BLEU	53.42	—	Unverified
2	TST	SARI	44.67	—	Unverified
3	UNSUP	BLEU	38.47	—	Unverified
4	DRESS-LS	BLEU	36.32	—	Unverified
5	DRESS	BLEU	34.53	—	Unverified
6	EditNTS	SARI	32.35	—	Unverified
7	NSELSTM-S	BLEU	29.72	—	Unverified
8	Pointer + Multi-task Entailment and Paraphrase Generation	BLEU	27.23	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	long-mBART (trained on DEplain-APA-doc)	SARI (EASSE>=0.2.1)	44.56	—	Unverified
2	long-mBART (trained on DEplain-APA-doc & DEplain-web-doc)	SARI (EASSE>=0.2.1)	42.86	—	Unverified
3	long-mBART (trained on DEplain-web-doc)	SARI (EASSE>=0.2.1)	35.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	long-mBART (trained on DEplain-APA-doc & DEplain-web-doc)	SARI (EASSE>=0.2.1)	49.75	—	Unverified
2	long-mBART (trained on DEplain-web-doc)	SARI (EASSE>=0.2.1)	49.58	—	Unverified
3	long-mBART (trained on DEplain-APA-doc)	SARI (EASSE>=0.2.1)	43.09	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SATS	SARI	40.83	—	Unverified
2	MedTSS-BART (Without Training)	Rouge1	35.17	—	Unverified
3	HTSS	Rouge1	21.94	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART (trained on DEplain-APA-sent & DEplain-web-sent)	SARI (EASSE>=0.2.1)	34.9	—	Unverified
2	mBART (trained on DEplain-APA-sent)	SARI (EASSE>=0.2.1)	34.82	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART (trained on DEplain-APA-sent & DEplain-web-sent)	SARI (EASSE>=0.2.1)	34.83	—	Unverified
2	mBART (trained on DEplain-APA-sent)	SARI (EASSE>=0.2.1)	30.87	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mT5 (fine-tuned on MULTI-SIM)	SARI	39.23	—	Unverified
2	LSTM	SARI	39.05	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART (TextBox 2.0)	BLEU-4	90.81	—	Unverified