مجردة نحن ندرس ملخصات نصية يمكن السيطرة عليها، والتي تتيح للمستخدمين السيطرة على سمة معينة (E.G.، الحد الطول) من الملخصات التي تم إنشاؤها.في هذا العمل، نقترح إطار تدريبي جديد يعتمد على عملية اتخاذ قرار ماركوف المقيد (CMDP)، والتي تتضمن ملاءمة وظيفة المكافأة إلى جانب مجموعة من القيود، لتسهيل سيطرة تلخيص أفضل.تشجع الوظيفة المكافأة على جيل تشبه المرجع الخطي البشري، في حين يتم استخدام القيود لتمنع بشكل صريح الملخصات التي تم إنشاؤها من انتهاك الاحتياجات التي يفرضها المستخدم.يمكن تطبيق إطارنا للتحكم في السمات المهمة من التلخيص، بما في ذلك الطول والكيانات المغطاة والتجريد، حيث أننا نضع قيود محددة لكل من هذه الجوانب.تبين تجارب واسعة النطاق على المعايير الشعبية أن إطار عمل مؤتمر الأطراف الخاص ب CMDP يساعد في توليد ملخصات إعلامية مع الامتثال لمتطلبات سمة معينة
Abstract We study controllable text summarization, which allows users to gain control on a particular attribute (e.g., length limit) of the generated summaries. In this work, we propose a novel training framework based on Constrained Markov Decision Process (CMDP), which conveniently includes a reward function along with a set of constraints, to facilitate better summarization control. The reward function encourages the generation to resemble the human-written reference, while the constraints are used to explicitly prevent the generated summaries from violating user-imposed requirements. Our framework can be applied to control important attributes of summarization, including length, covered entities, and abstractiveness, as we devise specific constraints for each of these aspects. Extensive experiments on popular benchmarks show that our CMDP framework helps generate informative summaries while complying with a given attribute's requirement.1
References used
https://aclanthology.org/
In this paper, we propose a controllable neural generation framework that can flexibly guide dialogue summarization with personal named entity planning. The conditional sequences are modulated to decide what types of information or what perspective t
Recent work on opinion summarization produces general summaries based on a set of input reviews and the popularity of opinions expressed in them. In this paper, we propose an approach that allows the generation of customized summaries based on aspect
Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph an
Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained
The research aims to study the effect of using immersive marketing techniques on the purchasing decision-making process, through its five stages, which include: the problem awareness stage, information gathering, alternatives evaluation, purchasing d