AI Paper Atlas

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

Translation-Based Matching Adversarial Network for Cross-Lingual Natural Language Inference

Kunxun Qi, Jianfeng Du

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 6 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
add TMAN framework (ablation)ESIM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 67.3 -> 69.0Improved
add domain adversarial network (ablation)ESIM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 67.9 -> 69.0Improved
add TMAN frameworkmultilingual BERT · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 72.0 -> 73.7Improved
add TMAN frameworkXLM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 76.7 -> 77.2Improved
add adversarial network (ablation)XLM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 76.1 -> 77.2Improved
mix 2 languages in a mini-batch (ablation)TMAN-XLM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 76.9 -> 77.2Improved
add transformer encoder (ablation)TMAN-XLM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 76.9 -> 77.2Improved
fixed cross-lingual word embeddings instead of ones used by TMAN-ESIM (ablation)TMAN-ESIM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 69.0 -> 68.7Hurt
updatable monolingual word embeddings (ablation)TMAN-ESIM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 69.0 -> 68.0Hurt
fixed monolingual word embeddings (ablation)TMAN-ESIM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 69.0 -> 67.7Hurt
random word embeddings (ablation)TMAN-ESIM · XNLI test, TRANSLATE-TRAIN, 15-language averageaccuracy (%): 69.0 -> 62.0Hurt
TMAN-XLM vs XLM on GermanTMAN-XLM · XNLI test, TRANSLATE-TRAIN, deaccuracy (%): 80.3 -> 80.2Hurt

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