# Bridging the domain gap in cross-lingual document classification Source: [Bridging the domain gap in cross-lingual document classification]() Collection index: [llms.txt]() Data updated: 2025-12-14T17:13:30.251Z Authors: Guokun Lai, Barlas Oguz, Yiming Yang, Veselin Stoyanov Published: 2019-09-16T06:20:23.000Z ## Abstract The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language barrier using language universal representations. However, even if the language problem was resolved, models trained in one language would not transfer to another language perfectly due to the natural domain drift across languages and cultures. We consider the setting of semi-supervised cross-lingual understanding, where labeled data is available in a source language (English), but only unlabeled data is available in the target language. We combine state-of-the-art cross-lingual methods with recently proposed methods for weakly supervised learning such as unsupervised pre-training and unsupervised data augmentation to simultaneously close both the language gap and the domain gap in XLU. We show that addressing the domain gap is crucial. We improve over strong baselines and achieve a new state-of-the-art for cross-lingual document classification. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [News Document Classification on MLDoc (test)](): News document classification; MLDoc (test); Error Rate (FR): 3.95. - [Sentiment classification on amazon fr (test)](): Sentiment Classification; amazon fr (test); Error Rate (%): 5.95. - [Sentiment Classification on Amazon DE (test)](): Sentiment Classification; amazon-de (test); Error Rate: 5.77. - [Sentiment classification on amazon-cn (test)](): Sentiment Classification; amazon-cn (test); Error Rate: 7.74. - [Sentiment Classification on dianping (test)](): Sentiment Classification; dianping (test); Error Rate: 0.0464. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()