Results 61 to 70 of about 2,563,850 (352)
Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network
Conference on Empirical Methods in Natural Language Processing, 2019 The lack of word boundaries information has been seen as one of the main obstacles to develop a high performance Chinese named entity recognition (NER) system.
Dianbo Sui +4 more
semanticscholar +1 more source
AAAI Conference on Artificial Intelligence, 2020 Spatial-temporal network data forecasting is of great importance in a huge amount of applications for traffic management and urban planning. However, the underlying complex spatial-temporal correlations and heterogeneities make this problem challenging ...
Chao Song +3 more
semanticscholar +1 more source
Predicting traffic propagation flow in urban road network with multi-graph convolutional network
Complex & Intelligent Systems, 2023 Traffic volume propagating from upstream road link to downstream road link is the key parameter for designing intersection signal timing scheme. Recent works successfully used graph convolutional network (GCN) and specific time-series model to forecast ...
Haiqiang Yang, Zihan Li, Yashuai Qi
semanticscholar +1 more source
New Turan-type bounds for Johnson graphs [PDF]
arXiv, 2021 In this paper, we consider the Johnson's graphs. We study the extremal properties of the Johnson's graphs. Namely, we investigate the number of edges in an arbitrary subgraph of this graph. Namely, in this article we prove analogs of Turan's 1941 theorem.
arxiv
Named entity disambiguation in short texts over knowledge graphs [PDF]
Knowledge and Information Systems, 2022 The ever-growing usage of knowledge graphs (KGs) positions named entity disambiguation (NED) at the heart of designing accurate KG-driven systems such as query answering systems (QAS). According to the current research, most studies dealing with NED on KGs involve long texts, which is not the case of short text fragments, identified by their limited ...
Wissem Bouarroudj +2 more
openaire +2 more sources
On the Sombor index and Sombor energy of m-splitting graph and m-shadow graph of regular graphs [PDF]
arXiv, 2022 A vertex-degree-based topological index named as Sombor index of a simple graph G with n vertices was recently introduced by I. Gutman. In this paper, we find Sombor index of m-splitting graph and m-shadow graph. Also, we determine relation between energy and Sombor energy of m-splitting graph and m-shadow graph of k-regular graph.
arxiv
Name disambiguation from link data in a collaboration graph [PDF]
2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014), 2014 The entity disambiguation task partitions the records belonging to multiple persons with the objective that each decomposed partition is composed of records of a unique person. Existing solutions to this task use either biographical attributes, or auxiliary features that are collected from external sources, such as Wikipedia.
Baichuan Zhang +2 more
openaire +2 more sources
Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks [PDF]
AAAI Conference on Artificial Intelligence, 2020 Social media has been developing rapidly in public due to its nature of spreading new information, which leads to rumors being circulated. Meanwhile, detecting rumors from such massive information in social media is becoming an arduous challenge ...
Tian Bian +6 more
semanticscholar +1 more source
BMC Bioinformatics, 2022 Background Automatic and accurate recognition of various biomedical named entities from literature is an important task of biomedical text mining, which is the foundation of extracting biomedical knowledge from unstructured texts into structured formats.
Xiangwen Zheng +5 more
doaj +1 more source
Using graph distances for named-entity linking
Science of Computer Programming, 2016 We formalize entity linking as an optimization problem.The problem is NP-hard but solvable in linear time under restrictive assumptions.We propose heuristics enforcing the assumptions or optimizing similar objectives.We show how our approaches perform w.r.t. some baselines on real data. Entity-linking is a natural-language-processing task that consists
Blanco Roi, Boldi Paolo, Marino Andrea
openaire +4 more sources