atlas

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

Bilingual Lexicon Induction from Non-Parallel Data with Minimal Supervision

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 30 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
add the matching term to the learning objective (vs seed term only) (ablation)bilingual embedding lexicon inducer · zh-en, 50 seedsaccuracyHelped
reduce seed lexicon from 100 to 10 pairs (ablation)Ours · zh-enaccuracyNo clear effect
reduce seed lexicon sizeTM, IA, STAT, BilBOWA baselines · zh-enaccuracyHurt
reduce seed lexicon to 10 for Turkish-English (ablation)Ours · tr-enaccuracyHurt
set matching weight too large (ablation)Ours · validation setaccuracyHurt
set matching weight too low (ablation)Ours · validation setaccuracyHurt
replace TM with IA (isometric constraint)translation matrix · es-en, 50 seedsaccuracy (%): 10.76 -> 32.36Helped

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