على الرغم من أن نماذج التلخيص المحظورة حققت نتائج مثيرة للإعجاب في مهام تلخيص المستندات، فإن أدائها على نمذجة الحوار أقل مرضية بأقل قدر ممكن بسبب الأساليب النفطية والمتصلة لترميز الحوار.لمعالجة هذا السؤال، نقترح نموذجا نزايدا للنماذج القائمة على المحولات في النهاية لتلخيص الحوار الجماعي الذي يرفع الهياكل الدلالية الدلالية الشديدة الحبوب إلى الحوار النموذجي وتوليد ملخصات أفضل.تجارب في برنامج Samsum DataSet الذي يجد يتفوق على مناهج تلخيص الحوار المختلفة وتحقق نتائج Rouge الحديثة (SOTA) الجديدة.أخيرا، نطبق أن نتمكن من العثور على سيناريو أكثر تعقيدا، مما يدل على تقلص نموذجنا.ونحن نطلق أيضا شفرة المصدر لدينا.
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 question, we propose a novel end-to-end Transformer-based model FinDS for abstractive dialogue summarization that leverages Finer-grain universal Dialogue semantic Structures to model dialogue and generates better summaries. Experiments on the SAMsum dataset show that FinDS outperforms various dialogue summarization approaches and achieves new state-of-the-art (SOTA) ROUGE results. Finally, we apply FinDS to a more complex scenario, showing the robustness of our model. We also release our source code.
References used
https://aclanthology.org/
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of t
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 dialogue summarization suffers from a lots of factual errors, which are due to scattered salient elements in the multi-speaker information interaction process. In this work, we design a heterogeneous semantic slot graph with a slot-level
The amount of information available online can be overwhelming for users to digest, specially when dealing with other users' comments when making a decision about buying a product or service. In this context, opinion summarization systems are of grea
Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon progressio