第二类是Spectral and Statistical Fingerprints，有7项研究的实现。比如，中选KDD 2018的NetLSD，不受排...
Cross-lingual Text Classification with Heterogeneous Graph Neural Network. Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu and Zhisheng Wang. ACL 2021 [pdf] Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations. Keerthiram Murugesan, Mattia Atzeni, ...
It is important to note that our approach is training the GNNetSlice model offline, meaning it is trained in the lab and later expected to be deployed in a production network. This approach is analogous to autonomous cars, which are trained by the vendor and then sold to customers already ...
The robot can observe the position of your face and the positions of surrounding objects and build a state recognition model based on the meaning and spatial location of those objects. A demonstration of the system in use is shown below. https://youtu.be/WI8vl_UJwCc Here, we first have...
Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification.Linmei Hu, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li.EMNLP 2019[pdf] Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes.Paulo Cavalin, Victor He...
Moreover, the number of meta-paths increases exponentially with the path length, meaning that it is almost infeasible to find all meaningful meta-paths to capture the high-order relationships. Furthermore, different meta-paths contribute differently to the community detection, which imposes great ...
Here, the translator retains the original metaphorical image in the translated text by translating literally.As a result of cultural interaction, more and more Chinese readers become aware of the figurative meaning of“sour grapes”, which indicates that one declaims something is bad only because he...
Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction. Zixuan Zhang and Heng Ji. NAACL 2021 [pdf] Event Time Extraction and Propagation via Graph Attention Networks. Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong and ...
Graph-level任务是一个图匹配任务，让图中所有节点pooling得到的embedding，和各个link predictoin任务中的...
1. 问题介绍 元学习（Meta learning）是今年来的研究热点。简单来说，元学习可以理解为"学会学习"，...