Onur Çelebi — accepted AI-conference papers

2023

xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages

Mingda Chen, Kevin Heffernan, Onur Çelebi, Alexandre Mourachko, Holger Schwenk

ACL 2023short

We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xsim++. In comparison to xsim, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which m…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2022

Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages

Kevin Heffernan, Onur Çelebi, Holger Schwenk

EMNLP 2022finding

Scaling multilingual representation learning beyond the hundred most frequent languages is challenging, in particular to cover the long tail of low-resource languages. We move away from the popular one-for-all multilingual models and focus on training multiple language (family) specific representati…

Cited by 87 Source ↗PDF ↗code ↗Scholar ↗