atlas

Research map / Large language models / Language, safety and interpretability

Idiomatic Expression Paraphrasing without Strong Supervision

AAAI 2022 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 10 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 iterative back-translation to augment the small parallel training setBART for idiomatic sentence paraphrasing · PIL test setBLEU: 78.53 -> 83.69Helped
Use iterative back-translation to augment the small parallel training setBART for idiomatic sentence paraphrasing · PIL test setSARI: 61.82 -> 81.39Helped
Use definition- and context-conditioned masked generation without parallel training dataBart-Ucd · PIL test setMETEOR: 85.36 -> 87.80Helped
Use Bart-Ibt paraphrasing as preprocessing before machine translationmBART · English-German challenge setBLEU: 10.1 -> 10.7Helped
Use iterative back-translation for idiomatic sentence generationBART for ISG · PIL test setBLEU: 79.32 -> 91.08Helped

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