حققت نماذج اللغة المرجعة متعددة اللغات متعددة اللغات مؤخرا أداءا ملحوظا عن الصفر، حيث يتم تقسيم النموذج فقط في لغة مصدر واحدة وتقييمها مباشرة على اللغات المستهدفة.في هذا العمل، نقترح إطارا للتعليم الذاتي الذي يستخدم البيانات غير المستهدفة من اللغات المستهدفة، بالإضافة إلى تقدير عدم اليقين في هذه العملية لتحديد ملصقات فضية عالية الجودة.يتم تكييف وثلاثة أوجه عدم اليقين الثلاثة وتحليلها خصيصا للتحويل اللغوي الصليب: لغة عدم اليقين المتنوعة من اللغة (LEU / LOU)، عدم اليقين الواضح (EVI).نقوم بتقييم إطار عملنا مع عدم اليقين على مهمتين متوقعتين بما في ذلك التعرف على الكيانات المسماة (NER) والاستدلال اللغوي الطبيعي (NLI) (NLI) (NLI) (NLI) تغطي 40 لغة في المجموع، والتي تتفوق على خطوط الأساس بشكل كبير بمقدار 10 F1 من دقة NLI.
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning framework that further utilizes unlabeled data of target languages, combined with uncertainty estimation in the process to select high-quality silver labels. Three different uncertainties are adapted and analyzed specifically for the cross lingual transfer: Language Heteroscedastic/Homoscedastic Uncertainty (LEU/LOU), Evidential Uncertainty (EVI). We evaluate our framework with uncertainties on two cross-lingual tasks including Named Entity Recognition (NER) and Natural Language Inference (NLI) covering 40 languages in total, which outperforms the baselines significantly by 10 F1 for NER on average and 2.5 accuracy for NLI.
References used
https://aclanthology.org/
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 across languages. Especially, le
We address the task of automatic hate speech detection for low-resource languages. Rather than collecting and annotating new hate speech data, we show how to use cross-lingual transfer learning to leverage already existing data from higher-resource l
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on high-resource lang
We study the problem of Cross-lingual Event Argument Extraction (CEAE). The task aims to predict argument roles of entity mentions for events in text, whose language is different from the language that a predictive model has been trained on. Previous
Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and equivalent complex tasks) often pertain to various types of sub-tasks, requiring di