إلى جانب توفر مجموعات بيانات واسعة النطاق، مكنت هياكل التعلم العميق التقدم السريع في مهمة الإجابة على السؤال.ومع ذلك، فإن معظم مجموعات البيانات هذه باللغة الإنجليزية، وأدائيات النماذج متعددة اللغات الحديثة أقل بكثير عند تقييمها على البيانات غير الإنجليزية.نظرا لتكاليف جمع البيانات العالية، فهي ليست واقعية للحصول على بيانات مشروحة لكل لغة رغبة واحدة لدعمها.نقترح طريقة لتحسين السؤال المتبادل الإجابة على الأداء دون الحاجة إلى بيانات مشروح إضافية، واستفادة نماذج توليد السؤال لإنتاج عينات اصطناعية في أزياء متصلة.نظهر أن الطريقة المقترحة تتيح التوفيق بشكل كبير على خطوط الأساس المدربين على بيانات اللغة الإنجليزية فقط.نبلغ عن أحدث طرف جديد في أربع مجموعات بيانات: MLQA و Xquad و Squad-It و PIAF (FR).
Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task. However, most of those datasets are in English, and the performances of state-of-the-art multilingual models are significantly lower when evaluated on non-English data. Due to high data collection costs, it is not realistic to obtain annotated data for each language one desires to support. We propose a method to improve the Cross-lingual Question Answering performance without requiring additional annotated data, leveraging Question Generation models to produce synthetic samples in a cross-lingual fashion. We show that the proposed method allows to significantly outperform the baselines trained on English data only. We report a new state-of-the-art on four datasets: MLQA, XQuAD, SQuAD-it and PIAF (fr).
References used
https://aclanthology.org/
We propose a simple method to generate multilingual question and answer pairs on a large scale through the use of a single generative model. These synthetic samples can be used to improve the zero-shot performance of multilingual QA models on target
Adapting word order from one language to another is a key problem in cross-lingual structured prediction. Current sentence encoders (e.g., RNN, Transformer with position embeddings) are usually word order sensitive. Even with uniform word form repres
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
Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed. We focus here on gloss-to-text
Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models. However, most existing techniques focus on augmenting in-domain data in low-resource scenarios where annotated data is quite limite