Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHeterogeneous Graph Neural Networks for Keyphrase Generation
الرسوم البيانية غير المتجانسة الشبكات العصبية لجيل المفتاح
324
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يحقق إطار التشفير - فك التشفير النتائج الحديثة النتائج في مهام توليد المفاتيح (KG) من خلال التنبؤ بكل من الرافعات القصيرة الحالية التي تظهر في المستند المصدر والمشابط الغياب التي لا تفعل ذلك. ومع ذلك، فإن الاعتماد فقط على المستند المصدر يمكن أن يؤدي إلى توليد قواعد الرماية الغائب لا يمكن السيطرة عليها وغير دقيقة. لمعالجة هذه المشكلات، نقترح طريقة رواية قائمة على الرسم البياني يمكنها التقاط المعرفة الصريحة من المراجع ذات الصلة. يتمتع نموذجنا أولا بتستريح بعض أزواج المفاتيح المستندات التي تشبه المستند المصدر من مؤشر محدد مسبقا كمراجع. ثم يتم بناء رسم بياني غير متجانس لالتقاط العلاقات مع مستويات مختلفة من الحبيبية المستند المصدر والمراجع المستردة لها. لتوجيه عملية فك التشفير، يتم تقديم اهتمام هرمي وآلية النسخ، والتي تنسخ مباشرة الكلمات المناسبة من كل من المستند المصدر ومراجعها بناء على أهميتها وأهميتها. تظهر النتائج التجريبية على معايير KG متعددة أن النموذج المقترح يحقق تحسينات كبيرة ضد نماذج خط الأساس الأخرى، خاصة فيما يتعلق بالتنبؤ الغياب بالصيغة الهادفة.
The encoder--decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not. However, relying solely on the source document can result in generating uncontrollable and inaccurate absent keyphrases. To address these problems, we propose a novel graph-based method that can capture explicit knowledge from related references. Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references. Then a heterogeneous graph is constructed to capture relations with different levels of granularity of the source document and its retrieved references. To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both source document and its references based on their relevance and significance. The experimental results on multiple KG benchmarks show that the proposed model achieves significant improvements against other baseline models, especially with regard to the absent keyphrase prediction.
References used
https://aclanthology.org/
rate research
Read More
Prerequisite relations among concepts are crucial for educational applications, such as curriculum planning and intelligent tutoring. In this paper, we propose a novel concept prerequisite relation learning approach, named CPRL, which combines both c
oncept representation learned from a heterogeneous graph and concept pairwise features. Furthermore, we extend CPRL under weakly supervised settings to make our method more practical, including learning prerequisite relations from learning object dependencies and generating training data with data programming. Our experiments on four datasets show that the proposed approach achieves the state-of-the-art results comparing with existing methods.
Multi-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such as document metadata or
label structure. These approaches however either simply utilize the semantic information of metadata or employ the predefined parent-child label hierarchy, ignoring the heterogeneous graphical structures of metadata and labels, which we believe are crucial for accurate multi-label document classification. Therefore, in this paper, we propose a novel neural network based approach for multi-label document classification, in which two heterogeneous graphs are constructed and learned using heterogeneous graph transformers. One is metadata heterogeneous graph, which models various types of metadata and their topological relations. The other is label heterogeneous graph, which is constructed based on both the labels' hierarchy and their statistical dependencies. Experimental results on two benchmark datasets show the proposed approach outperforms several state-of-the-art baselines.
External syntactic and semantic information has been largely ignored by existing neural coreference resolution models. In this paper, we present a heterogeneous graph-based model to incorporate syntactic and semantic structures of sentences. The prop
osed graph contains a syntactic sub-graph where tokens are connected based on a dependency tree, and a semantic sub-graph that contains arguments and predicates as nodes and semantic role labels as edges. By applying a graph attention network, we can obtain syntactically and semantically augmented word representation, which can be integrated using an attentive integration layer and gating mechanism. Experiments on the OntoNotes 5.0 benchmark show the effectiveness of our proposed model.
Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle
relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.
The work aims to make benefit from existence
multi-CPU and multi-GPU, exploiting the calculation processes
which do multi-GPU, which aims to form mechanism to
scheduling a directed acyclic graph(DAG), it aims to reduce
communication between resources and inter linked task
scheduling in the best form.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
