بدافع من جيل السؤال المقترح في أنظمة توصية أخبار المحادلات، نقترح نموذجا لتوليد أزواج الإجابات السؤال (أزواج ضمان الجودة) مع أسئلة ذاتية التركيز ذاتي ومقيد الطول، إجابات تلخص المادة.نبدأ بجمع مجموعة بيانات جديدة من المقالات الإخبارية مع أسئلة كعناوين واقترانها مع ملخصات طول متفاوتة.يتم استخدام هذه البيانات هذه البيانات لتعلم ملخصات إنتاج نموذج توليد QA للزوج كجابات توازن الرصيد بالإيجاز مع الاكتفاء بالاشتراك مع أسئلتها المقابلة.ثم نعزز عملية توليد زوج ضمان الجودة مع وظيفة مكافأة مختلفة لتخفيف تحيز التعرض، وهي مشكلة شائعة في توليد اللغة الطبيعية.يظهر كل من المقاييس التلقائية والتقييم البشري هذه أزواج ضمان الجودة بنجاح التقاط القابس المركزي للمقالات وتحقيق دقة عالية للإجابة.
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing answers. We begin by collecting a new dataset of news articles with questions as titles and pairing them with summaries of varying length. This dataset is used to learn a QA pair generation model producing summaries as answers that balance brevity with sufficiency jointly with their corresponding questions. We then reinforce the QA pair generation process with a differentiable reward function to mitigate exposure bias, a common problem in natural language generation. Both automatic metrics and human evaluation demonstrate these QA pairs successfully capture the central gists of the articles and achieve high answer accuracy.
References used
https://aclanthology.org/
Generating high quality question-answer pairs is a hard but meaningful task. Although previous works have achieved great results on answer-aware question generation, it is difficult to apply them into practical application in the education field. Thi
In education, quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far,
Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel training schemes for spoken question answering with a self-supervised traini
We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web page
Despite excellent performance on tasks such as question answering, Transformer-based architectures remain sensitive to syntactic and contextual ambiguities. Question Paraphrasing (QP) offers a promising solution as a means to augment existing dataset