يتطلب إجابة السؤال المستندة إلى السيناريو (SQA) على استرداد وقراءة الفقرات من كوربوس كبيرة للإجابة على سؤال محكوم بموجب وصف سيناريو طويل.نظرا لأن السيناريو يحتوي على كلا القصاصات الاسترجاع والكثير من الضوضاء، فإن استرجاع SQA صعب للغاية.علاوة على ذلك، بالكاد يمكن أن يشرف عليه بسبب عدم وجود ملصقات ذات صلة من الفقرات ل SQA.لتلبية التحدي، في هذه الورقة نقترح نموذج قارئ مسترجع مشترك يسمى Jeeves حيث يتم الإشراف على المسترد الضمني فقط باستخدام ملصقات ضمان الجودة عبر آلية ترجيح كلمة جديدة.يتفوق Jeeves بشكل كبير على مجموعة متنوعة من خطوط الأساس القوية على أسئلة متعددة الخيارات في ثلاث مجموعات بيانات SQA.
Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description. Since a scenario contains both keyphrases for retrieval and much noise, retrieval for SQA is extremely difficult. Moreover, it can hardly be supervised due to the lack of relevance labels of paragraphs for SQA. To meet the challenge, in this paper we propose a joint retriever-reader model called JEEVES where the retriever is implicitly supervised only using QA labels via a novel word weighting mechanism. JEEVES significantly outperforms a variety of strong baselines on multiple-choice questions in three SQA datasets.
References used
https://aclanthology.org/
Multiple-choice questions (MCQs) are widely used in knowledge assessment in educational institutions, during work interviews, in entertainment quizzes and games. Although the research on the automatic or semi-automatic generation of multiple-choice t
Large language models have become increasingly difficult to train because of the growing computation time and cost. In this work, we present SRU++, a highly-efficient architecture that combines fast recurrence and attention for sequence modeling. SRU
Machine Reading Comprehension (MRC), which requires a machine to answer questions given the relevant documents, is an important way to test machines' ability to understand human language. Multiple-choice MRC is one of the most studied tasks in MRC du
Character-based word-segmentation models have been extensively applied to agglutinative languages, including Thai, due to their high performance. These models estimate word boundaries from a character sequence. However, a character unit in sequences
Transformer-based neural networks offer very good classification performance across a wide range of domains, but do not provide explanations of their predictions. While several explanation methods, including SHAP, address the problem of interpreting