Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching
Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word representations. However, uncontrolled and over-replaced code-switching would augment dirty samples to model training. In other words, the excessive code-switching text samples will negatively hurt the models' cross-lingual transferability. To this end, we propose a Progressive Code-Switching (PCS) method to gradually generate moderately difficult code-switching examples for the model to discriminate from easy to hard. The idea is to incorporate progressively the preceding learned multilingual knowledge using easier code-switching data to guide model optimization on succeeding harder code-switching data. Specifically, we first design a difficulty measurer to measure the impact of replacing each word in a sentence based on the word relevance score. Then a code-switcher generates the code-switching data of increasing difficulty via a controllable temperature variable. In addition, a training scheduler decides when to sample harder code-switching data for model training. Experiments show our model achieves state-of-the-art results on three different zero-shot cross-lingual transfer tasks across ten languages.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Lingual TransferData AugmentationModel OptimizationSentenceZero-Shot Cross-Lingual TransferSimilar Papers 제목 키워드 기반
Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual tr…
Cross-Lingual TransferTopic ClassificationTranslationZero-Shot Cross-Lingual TransferRealistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
We consider zero-shot cross-lingual transfer in legal topic classification using the recent Multi-EURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual t…
ClassificationCross-Lingual TransferTopic ClassificationTranslation+1Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer
Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in languages with more sufficient training resources to generalize to other low-resource languages. Earlier efforts on this …
Cross-Lingual TransferMultilingual NLPZero-Shot Cross-Lingual TransferImproving Zero-Shot Cross-Lingual Transfer Learning via Robust Training
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases ac…
Cross-Lingual TransferSentencetext-classificationText Classification+3Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model
Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning o…
Cross-Lingual TransferReading ComprehensionTransfer LearningZero-Shot Cross-Lingual Transfer+1