تشبه مهمة تبسيط نص الوثيقة على مستوى المستندات إلى صعوبة تقليل التعقيد الإضافي.نقدم مجموعة بيانات مجمعة حديثا من النصوص الألمانية، التي تم جمعها من مجلة Swiss News 20 Minuten (20 دقيقة) والتي تتكون من مقالات كاملة مقررة مع ملخصات مبسطة.علاوة على ذلك، نقدم تجارب على تبسيط النص التلقائي مع MBART MBART متعددة اللغات المسبدة مسبقا ونسخة معدلة منها أكثر صديقة للذاكرة، باستخدام كل من مجموعة البيانات الجديدة والتبسيط الموجودة Corpora.تتيح لنا تعديلات MBArt التدريب بتكلفة أقل في الذاكرة دون فقدان الكثير من الخسارة في الأداء، في الواقع، فإن MBART أصغر يحسن حتى النموذج القياسي في إعداد مع مستويات تبسيط متعددة.
The task of document-level text simplification is very similar to summarization with the additional difficulty of reducing complexity. We introduce a newly collected data set of German texts, collected from the Swiss news magazine 20 Minuten (20 Minutes') that consists of full articles paired with simplified summaries. Furthermore, we present experiments on automatic text simplification with the pretrained multilingual mBART and a modified version thereof that is more memory-friendly, using both our new data set and existing simplification corpora. Our modifications of mBART let us train at a lower memory cost without much loss in performance, in fact, the smaller mBART even improves over the standard model in a setting with multiple simplification levels.
References used
https://aclanthology.org/
Text simplification is a valuable technique. However, current research is limited to sentence simplification. In this paper, we define and investigate a new task of document-level text simplification, which aims to simplify a document consisting of m
As the world continues to fight the COVID-19 pandemic, it is simultaneously fighting an infodemic' -- a flood of disinformation and spread of conspiracy theories leading to health threats and the division of society. To combat this infodemic, there i
Reviewing contracts is a time-consuming procedure that incurs large expenses to companies and social inequality to those who cannot afford it. In this work, we propose document-level natural language inference (NLI) for contracts'', a novel, real-wor
Automatic personalized corrective feedback can help language learners from different backgrounds better acquire a new language. This paper introduces a learner English dataset in which learner errors are accompanied by information about possible erro
The paper introduces a new resource, CoDeRooMor, for studying the morphology of modern Swedish word formation. The approximately 16.000 lexical items in the resource have been manually segmented into word-formation morphemes, and labeled for their ca