نماذج تلخيص التعلم العميق الأخيرة (DL) تتفوق بشكل كبير من منهجيات التلخصات التقليدية، وتوليد ملخصات عالية الجودة. على الرغم من نجاحهم، لا تزال هناك مشكلات مفتوحة مهمة، مثل المشاركة المحدودة والثقة للمستخدمين في العملية برمتها. من أجل التغلب على هذه القضايا، نعيد النظر في مهمة التلخيص من منظور متمركز الإنسان. نقترح دمج واجهة المستخدم بنموذج DL الأساسي، بدلا من معالجة التلخيص كامرأة معزولة من المستخدم النهائي. نقدم نظام جديد، حيث يمكن للمستخدم المشاركة بنشاط في عملية التلخيص بأكملها. كما يمكننا المستخدم من جمع الأفكار في العوامل المسببة التي تدفع سلوك النموذج، واستغلال آلية اهتمام الذات. نحن نركز على المجال المالي، من أجل إظهار كفاءة نماذج DL العامة للتطبيقات الخاصة بالمجال. يتخذ عملنا خطوة أولى نحو نهج تصميم مشترك للواجهة النموذجية، حيث تتطور نماذج DL على طول احتياجات المستخدمين، مما يمهد الطريق نحو واجهات تلخيص نص الحاسوب البشري.
Recent Deep Learning (DL) summarization models greatly outperform traditional summarization methodologies, generating high-quality summaries. Despite their success, there are still important open issues, such as the limited engagement and trust of users in the whole process. In order to overcome these issues, we reconsider the task of summarization from a human-centered perspective. We propose to integrate a user interface with an underlying DL model, instead of tackling summarization as an isolated task from the end user. We present a novel system, where the user can actively participate in the whole summarization process. We also enable the user to gather insights into the causative factors that drive the model's behavior, exploiting the self-attention mechanism. We focus on the financial domain, in order to demonstrate the efficiency of generic DL models for domain-specific applications. Our work takes a first step towards a model-interface co-design approach, where DL models evolve along user needs, paving the way towards human-computer text summarization interfaces.
References used
https://aclanthology.org/
In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumpti
Interpretability or explainability is an emerging research field in NLP. From a user-centric point of view, the goal is to build models that provide proper justification for their decisions, similar to those of humans, by requiring the models to sati
The aim of this research is to investigate the effect of preparing the
financial statements through International Accounting Standard /29/ on
the financial analysis through ratios, since the increase in the inflation
rate affects social and econom
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
We consider the problem of topic-focused abstractive summarization, where the goal is to generate an abstractive summary focused on a particular topic, a phrase of one or multiple words. We hypothesize that the task of generating topic-focused summar