تم اعتماد الأساليب القائمة على الرسم البياني مؤخرا لتلخيص نص مبادرة.ومع ذلك، فإن الأساليب القائمة على الرسم البياني الموجودة فقط تنظر فقط في علاقات الكلمات أو معلومات الهيكل، والتي تهمل الارتباط بينهما.في وقت واحد التقاط علاقات الكلمة ومعلومات الهيكل من الجمل، نقترح شبكة الرسم البياني المزدوج الرواية لتلخيص جملة الاختيارات.على وجه التحديد، نقوم أولا بإنشاء رسم بياني للسيناريو الدلالي والكلمة الدلالية الرسم البياني على أساس FRAMENET، وبالتالي تعلم تمثيلاتها وطريقة الانصهار الرسم البياني للتصميم لتعزيز ارتباطها والحصول على تمثيل دلالي أفضل لجيل الملخص.تظهر النتائج التجريبية النموذج لدينا تفوق الأساليب الموجودة في مجموعة بيانات قياسية شعبية، I.E.، GIGAWORD و DUC 2004.
Recently graph-based methods have been adopted for Abstractive Text Summarization. However, existing graph-based methods only consider either word relations or structure information, which neglect the correlation between them. To simultaneously capture the word relations and structure information from sentences, we propose a novel Dual Graph network for Abstractive Sentence Summarization. Specifically, we first construct semantic scenario graph and semantic word relation graph based on FrameNet, and subsequently learn their representations and design graph fusion method to enhance their correlation and obtain better semantic representation for summary generation. Experimental results show our model outperforms existing state-of-the-art methods on two popular benchmark datasets, i.e., Gigaword and DUC 2004.
References used
https://aclanthology.org/
ROUGE is a widely used evaluation metric in text summarization. However, it is not suitable for the evaluation of abstractive summarization systems as it relies on lexical overlap between the gold standard and the generated summaries. This limitation
Abstractive summarization models heavily rely on copy mechanisms, such as the pointer network or attention, to achieve good performance, measured by textual overlap with reference summaries. As a result, the generated summaries stay close to the form
Sentence-level extractive text summarization aims to select important sentences from a given document. However, it is very challenging to model the importance of sentences. In this paper, we propose a novel Frame Semantic-Enhanced Sentence Modeling f
How do people understand the meaning of the word small'' when used to describe a mosquito, a church, or a planet? While humans have a remarkable ability to form meanings by combining existing concepts, modeling this process is challenging. This paper
Although abstractive summarization models have achieved impressive results on document summarization tasks, their performance on dialogue modeling is much less satisfactory due to the crude and straight methods for dialogue encoding. To address this