AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Unsupervised Lexical Simplification for Non-Native Speakers

Gustavo Paetzold, Lucia Specia

AAAI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 114 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use POS-tag-annotated context-aware embeddings instead of standard embeddings for generationembedding-based substitution generator · NNSevalF1: 0.121 -> 0.136Improved
add unsupervised boundary-ranking substitution selectionLS-NNS generator output · NNSevalF1: 0.136 -> 0.156Improved
add WSD-based selection (Lesk)LS-NNS generator output · NNSevalF1: 0.136 -> 0.037Hurt
rank by frequencies from children/family subtitle corpus (SubIMDB) instead of Google 1Tfrequency ranker · SemEval 2012 LSTRank: 0.585 -> 0.627Improved
use small Brown corpus instead of huge Google 1Tfrequency ranker · SemEval 2012 LSTRank: 0.585 -> 0.596Improved
full LS-NNS pipeline vs Glavaslexical simplification · NNSeval round-tripAccuracy: 0.197 -> 0.226Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy