ASSET

Dataset Information
Modalities
Texts
Introduced
2020
License
Unknown
Homepage
Official Website
Contents

Overview

ASSET is a new dataset for assessing sentence simplification in English. ASSET is a crowdsourced multi-reference corpus where each simplification was produced by executing several rewriting transformations.

Source: ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations

Variants: ASSET

Associated Benchmarks

This dataset is used in 1 benchmark:

  • Text Simplification - Metrics: BLEU, SARI (EASSE>=0.2.1), METEOR, FKGL, QuestEval (Reference-less, BERTScore)

Recent Benchmark Submissions

Task Model Paper Date
Text Simplification GPT-175B (15 SARI-selected examples, random ordering) Metric-Based In-context Learning: A Case … 2023-07-27
Text Simplification Control Prefixes (BART) Control Prefixes for Parameter-Efficient Text … 2021-10-15
Text Simplification TST Text Simplification by Tagging 2021-03-08
Text Simplification BART The GEM Benchmark: Natural Language … 2021-02-02
Text Simplification T5 The GEM Benchmark: Natural Language … 2021-02-02
Text Simplification MUSS (BART+ACCESS Supervised) MUSS: Multilingual Unsupervised Sentence Simplification … 2020-05-01
Text Simplification MUSS (BART+ACCESS Unsupervised) MUSS: Multilingual Unsupervised Sentence Simplification … 2020-05-01
Text Simplification ACCESS Controllable Sentence Simplification 2019-10-07
Text Simplification DMASS-DCSS Integrating Transformer and Paraphrase Rules … 2018-10-26
Text Simplification UNTS (Unsupervised) Unsupervised Neural Text Simplification 2018-10-18
Text Simplification Dress-LS Sentence Simplification with Deep Reinforcement … 2017-03-31

Research Papers

Recent papers with results on this dataset:

External Links: