نقدم طلب النظام من فريق FastPlse للمهمة المشتركة EUD في IWPT 2021. نشارك في المهمة العام الماضي من خلال التركيز على الكفاءة.لقد ركزنا هذا العام على تجربة الأفكار الجديدة في ميزانية زمنية محدودة.يعتمد نظامنا على تقسيم الرسم البياني Eud إلى العديد من الأشجار، بناء على المعايير اللغوية.نتنبأ هذه الأشجار باستخدام محلل تسمية التسلسل ودمجها في رسم بياني Eud.كانت النتائج فقراء نسبيا، على الرغم من عدم وجود كارثة إجمالية وربما تم تحسينها مع بعض تلميع الحواف الخشنة للنظام.
We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2021. We engaged in the task last year by focusing on efficiency. This year we have focused on experimenting with new ideas on a limited time budget. Our system is based on splitting the EUD graph into several trees, based on linguistic criteria. We predict these trees using a sequence-labelling parser and combine them into an EUD graph. The results were relatively poor, although not a total disaster and could probably be improved with some polishing of the system's rough edges.
References used
https://aclanthology.org/
Infusing factual knowledge into pre-trained models is fundamental for many knowledge-intensive tasks. In this paper, we proposed Mixture-of-Partitions (MoP), an infusion approach that can handle a very large knowledge graph (KG) by partitioning it in
Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a setting where hand-annotated q
Recipe texts are an idiosyncratic form of instructional language that pose unique challenges for automatic understanding. One challenge is that a cooking step in one recipe can be explained in another recipe in different words, at a different level o
Recent transformer-based approaches demonstrate promising results on relational scientific information extraction. Existing datasets focus on high-level description of how research is carried out. Instead we focus on the subtleties of how experimenta
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, sy