حققت نماذج متعددة اللغات المدربة مسبقا أداء ملحوظا على تعلم التحويل عبر اللغات.تم تدريب بعض النماذج متعددة اللغات مثل Mbert، مدربة مسبقا على Corpora غير المسبق، وبالتالي لا يمكن تضمين تضمينات لغات مختلفة في النماذج بشكل جيد للغاية.في هذه الورقة، نهدف إلى تحسين أداء نقل اللغات المتبادل الصفر عن طريق اقتراح مهمة تدريبية مسبقا تسمى نموذج محاذاة Word-Exchange (Weal)، والذي يستخدم معلومات المحاذاة الإحصائية كمعرفة مسبقة لتوجيه الكلمة عبر اللغاتتنبؤ.نحن نقيم نموذجنا في مهمة مهام الفهم لقراءة الجهاز متعدد اللغات ومهمة واجهة اللغة الطبيعية XNLI.تظهر النتائج أن Weam يمكن أن يحسن بشكل كبير من الأداء الصفر بالرصاص.
Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.
References used
https://aclanthology.org/
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextual multilingual multimodal embeddings. Under a zero-s
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
Multilingual question answering over knowledge graph (KGQA) aims to derive answers from a knowledge graph (KG) for questions in multiple languages. To be widely applicable, we focus on its zero-shot transfer setting. That is, we can only access train
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 present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlappin