AI Paper Atlas

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

Simplify-Then-Translate: Automatic Preprocessing for Black-Box Translation

Sneha Mehta, Bahareh Azarnoush, Boris Chen, Avneesh Saluja, Vinith Misra, Ballav Bihani, Ritwik Kumar

AAAI 2020 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 18 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
Preprocess source with the in-domain FIGS APP modelGoogle Translate · FIGS low-resource translation: En-Hu, En-Uk, En-Cs, En-Ro, En-Bg, En-Hi, En-MsBLEU: 17.69 -> 18.92; 17.57 -> 18.18; 21.62 -> 22.35; 26.08 -> 27.98; 14.9 -> 16.63; 14.45 -> 15.53; 19.14 -> 20.37Improved
Preprocess source with the WikiLarge-trained simplification model instead of the in-domain modelGoogle Translate · FIGS low-resource translationBLEU: 17.69 -> 11.86; 17.57 -> 12.51; 21.62 -> 16.71; 26.08 -> 21.56; 14.9 -> 12.39; 14.45 -> 11.39; 19.14 -> 13.00Hurt
Preprocess source with En-Es-trained APPGoogle Translate · Open Subtitles En-Ca and En-PtBLEU: 27.25 -> 27.84; 25.11 -> 25.5Improved
Preprocess source with En-Es-trained APPGoogle Translate · Open Subtitles En-BgBLEU: 23.71 -> 24.68Improved
Preprocess source with En-Es-trained APPGoogle Translate · Open Subtitles En-Hu and En-RoBLEU: 7.05 -> 6.28; 26.18 -> 25.03Hurt
Preprocess source with En-Es-trained APPGoogle Translate · Open Subtitles En-UkBLEU: 11.73 -> 11.77No clear effect
Use En-Es rather than En-Ru to generate the APP training corpusAPP simplification model · TurkSARI: 23.2 -> 26.7Improved
Use En-Es rather than En-Ru to generate the APP training corpusAPP simplification model · PWKP test setBLEU: 23.9 -> 32.7Improved
Use a more easily translated En-Es pair rather than En-Ru for APP corpus generationAPP simplification model · Open Subtitles En-Ca, En-Pt, En-Ro, En-Uk, En-BgBLEU: En-Ca: 23.36 -> 27.84; En-Pt: 22.28 -> 25.5; En-Ro: 22.40 -> 25.03; En-Uk: 11.61 -> 11.77; En-Bg: 23.90 -> 24.68Mixed
Simplify source with APP before translationGoogle Translate · FIGS test setTER: 6.9%, 6.9% and 7.2% reduction for Hungarian, Romanian and BulgarianImproved
Simplify source with APP before translationGoogle Translate · Human evaluation: En-Hu, En-Uk, En-Cs, En-Ro, En-Bgmean human rating: 2.52 -> 3.11; 3.02 -> 3.61; 2.43 -> 3.12; 2.56 -> 3.0; 2.34 -> 3.33Improved

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