Filters








1,265 Hits in 2.8 sec

Diachronic Embedding for Temporal Knowledge Graph Completion

Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker, Pascal Poupart
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times.  ...  In this paper, we build novel models for temporal KG completion through equipping static models with a diachronic entity embedding function which provides the characteristics of entities at any point in  ...  A temporal knowledge graph (KG) G is a subset of W (i.e. G ⊂ W) 1 . Temporal KG completion (TKGC) is the problem of inferring W from G.  ... 
doi:10.1609/aaai.v34i04.5815 fatcat:ydt2jj2zzvacrcgeyedgbd2j7e

Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations [article]

Zhen Han, Ruotong Liao, Beiyan Liu, Yao Zhang, Zifeng Ding, Jindong Gu, Heinz Köppl, Hinrich Schütze, Volker Tresp
2022 arXiv   pre-print
Experimental results on the temporal knowledge graph completion task show that ECOLA outperforms state-of-the-art temporal KG models by a large margin.  ...  information from descriptions into temporal knowledge embeddings.  ...  We use the code for TNTCopmlEx from the tKG framework [Han et al., 2021a] . We implement TTransE based on the  ... 
arXiv:2203.09590v3 fatcat:vovdzstpzrcmlnray7ojmplhtq

Modelling graph dynamics in fraud detection with "Attention" [article]

Susie Xi Rao, Clémence Lanfranchi, Shuai Zhang, Zhichao Han, Zitao Zhang, Wei Min, Mo Cheng, Yinan Shan, Yang Zhao, Ce Zhang
2022 arXiv   pre-print
We first construct dynamic heterogeneous graphs from registration and transaction data from eBay. Then, we build models with diachronic entity embedding and heterogeneous graph transformer.  ...  Despite the variety of different models for deep learning on graphs, few approaches have been proposed for dealing with graphs that are both heterogeneous and dynamic.  ...  The use of diachronic embedding has proved beneficial in temporal knowledge graph (KG) completion.  ... 
arXiv:2204.10614v1 fatcat:qzdwnp2ju5h4xo2dqynkhd56l4

ChronoR: Rotation Based Temporal Knowledge Graph Embedding [article]

Ali Sadeghian, Mohammadreza Armandpour, Anthony Colas, Daisy Zhe Wang
2021 arXiv   pre-print
We propose Chronological Rotation embedding (ChronoR), a novel model for learning representations for entities, relations, and time.  ...  Experimentally, we show that ChronoR is able to outperform many of the state-of-the-art methods on the benchmark datasets for temporal knowledge graph link prediction.  ...  Similarly, temporal knowledge graph embedding methods learn an additional mapping for time.  ... 
arXiv:2103.10379v1 fatcat:youltcrzdfclzd2z2ip3fpwosu

Temporal Knowledge Graph Completion using Box Embeddings [article]

Johannes Messner, Ralph Abboud, İsmail İlkan Ceylan
2021 arXiv   pre-print
Temporal knowledge graph completion (TKGC) is an extension of this task to temporal knowledge graphs, where each fact is additionally associated with a time stamp.  ...  In this paper, we propose BoxTE, a box embedding model for TKGC, building on the static knowledge graph embedding model BoxE.  ...  In this paper, we propose BoxTE, a box embedding model for temporal knowledge graph completion.  ... 
arXiv:2109.08970v1 fatcat:nvwg7do3arcn7damimes7ibcgu

Exploring Diachronic Changes of Biomedical Knowledge using Distributed Concept Representations

Gaurav Vashisth, Jan-Niklas Voigt-Antons, Michael Mikhailov, Roland Roller
2019 Proceedings of the 18th BioNLP Workshop and Shared Task  
This work instead examines the evolution in biomedical knowledge over time using scientific literature in terms of diachronic change.  ...  Mainly the usage of temporal and distributional concept representations are explored and evaluated by a proof-of-concept.  ...  In addition to that we would like to thank our colleagues for their feedback and suggestions.  ... 
doi:10.18653/v1/w19-5037 dblp:conf/bionlp/VashisthVMR19 fatcat:h6d5gyzc2bh6refctktb32iu54

Spatio-Temporal Urban Knowledge Graph Enabled Mobility Prediction [article]

Huandong Wang, Qiaohong Yu, Yu Liu, Depeng Jin, Yong Li
2021 arXiv   pre-print
Further, a complex embedding model with elaborately designed scoring functions is proposed to measure the plausibility of facts in STKG to solve the knowledge graph completion problem, which considers  ...  The mobility prediction problem is converted to the knowledge graph completion problem in STKG.  ...  There exist other techniques of knowledge graph embedding that utilize the continuous temporal information, e.g., diachronic embedding [9] .  ... 
arXiv:2111.03465v2 fatcat:scaluj6f2rcvdmb2xno4jmreoe

Computational approaches to lexical semantic change: Visualization systems and novel applications [chapter]

Adam Jatowt, Nina Tahmasebi, Lars Borin
2021 Zenodo  
Developing interactive, visual, engaging, and easy-to-understand systems can help them to acquire relevant knowledge.  ...  The purpose of this chapter is to survey visualization and user interface solutions for understanding lexical semantic change as well as to survey a number of applications of techniques developed in computational  ...  (2016) is composed of two kinds of complementary graphs: a stream graph and a series of network graphs.  ... 
doi:10.5281/zenodo.5040320 fatcat:knrbwnsd7ne7rihw72m4hkfcba

Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining [article]

Lei Yu, Yang Xu
2021 arXiv   pre-print
We find support for an exemplar view of chaining as opposed to a prototype view and reveal how the joint approach of multimodal chaining may be fundamental to the creation of literal and figurative language  ...  We develop a framework that exploits the cognitive mechanisms of chaining and multimodal knowledge to predict emergent compositional expressions through time.  ...  for helpful suggestions.  ... 
arXiv:2109.04652v1 fatcat:z2ckogh2ebbezdg3y5umdqjvfq

QMUL-SDS @ DIACR-Ita: Evaluating Unsupervised Diachronic Lexical Semantics Classification in Italian [article]

Rabab Alkhalifa, Adam Tsakalidis, Arkaitz Zubiaga, Maria Liakata
2020 arXiv   pre-print
We demonstrate that using Temporal Word Embeddings with a Compass C-BOW model is more effective compared to different approaches including Logistic Regression and a Feed Forward Neural Network using accuracy  ...  The task involves training, aligning and predicting a word's vector change from two diachronic Italian corpora.  ...  Temporal Word Embeddings with a Compass (TWEC) (Carlo et al., 2019) approach uses an approach of freezing selected vectors based on model's architecture, it learn a parallel embedding for all time periods  ... 
arXiv:2011.02935v2 fatcat:ftz3tdcerfcu3ojfisrzvyr2oa

3DRTE: 3D Rotation Embedding in Temporal Knowledge Graph

Jingbin Wang, Wang Zhang, Xinyuan Chen, Jing Lei, Xiaolian Lai
2020 IEEE Access  
Temporal Knowledge Graph (TKG) describes each time fact in the form of a quadruple: (head, relation, tail, time) and Temporal Knowledge Graph Completion (TKGC) emerges, introducing temporal characteristics  ...  knowledge graph embedding model 3DRTE is proposed.  ... 
doi:10.1109/access.2020.3036897 fatcat:vodef7tbrrdy3dcq4dczkbqepq

TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion [article]

Jiapeng Wu, Yishi Xu, Yingxue Zhang, Chen Ma, Mark Coates, Jackie Chi Kit Cheung
2021 arXiv   pre-print
Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently.  ...  To address these challenges, we present the Time-aware Incremental Embedding (TIE) framework, which combines TKG representation learning, experience replay, and temporal regularization.  ...  The authors would like to thank Noah's Ark Lab for providing the computational resources.  ... 
arXiv:2104.08419v3 fatcat:sx6nodkoivgnbnkw6ip43wxn5q

Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition [article]

Chengjin Xu and Mojtaba Nayyeri and Fouad Alkhoury and Hamed Shariat Yazdi and Jens Lehmann
2020 arXiv   pre-print
Knowledge Graph (KG) embedding has attracted more attention in recent years. Most KG embedding models learn from time-unaware triples.  ...  The mean of each entity/relation embedding at a time step shows the current expected position, whereas its covariance (which is temporally stationary) represents its temporal uncertainty.  ...  Introduction Knowledge Graphs (KGs) are being used for gathering and organizing scattered human knowledge into structured knowledge systems.  ... 
arXiv:1911.07893v6 fatcat:nw5n7xrdvzewvlnwztt3tlkuky

Hyperplane-based time-aware knowledge graph embedding for temporal knowledge graph completion

Peng He, Gang Zhou, Hongbo Liu, Yi Xia, Ling Wang
2022 Journal of Intelligent & Fuzzy Systems  
Knowledge Graph (KG) embedding approaches have been proved effective to infer new facts for a KG based on the existing ones–a problem known as KG completion.  ...  In this paper, we propose a new hyperplane-based time-aware KG embedding model for temporal KG completion.  ...  To address the above issues, we propose a novel Hyperplane-based Time-aware Knowledge graph Embedding model named HTKE for temporal KG completion.  ... 
doi:10.3233/jifs-211950 fatcat:bxe4yz2mnfaohbk56g4rpbxhki

Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures [article]

Sebastien Montella, Lina Rojas-Barahona, Johannes Heinecke
2021 arXiv   pre-print
Knowledge Graph (KG) completion has been excessively studied with a massive number of models proposed for the Link Prediction (LP) task.  ...  Indeed, the temporal aspect of stored facts is often ignored. To this end, more and more works consider time as a parameter to complete KGs.  ...  knowledge graphs.  ... 
arXiv:2106.04311v1 fatcat:qgrdxmx2ufeurdipzf625ve4uu
« Previous Showing results 1 — 15 out of 1,265 results