Text-Augmented Knowledge Representation Learning Based on Convolutional Network

Liu, Chunfeng; Zhang, Yan; Yu, Mo; Yu, Ruiguo; Li, Xuewei; Zhao, Mankun; Xu, Tianyi; Liu, Hongwei; Yu, Jian

doi:10.1007/978-3-030-36708-4_16

Cited by 7 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparative baseline models used in this experiment fall into two categories: triple-based methods (TransE [ 9 ], TransH [ 10 ], ConvE [ 12 ], ConvKB [ 25 ], R-GCN [ 40 ], RotatE [ 11 ], and MRotatE [ 24 ]) as well as methods that integrate text information (DKRL [ 14 ], Jointly [ 32 ], TEKE_E [ 43 ], AATE_E [ 35 ], ConMask [ 15 ], TA-ConvKB [ 36 ], BCRL [ 44 ], Pretrain-KGE [ 37 ], and TEGER [ 16 ]).…”

Section: Resultsmentioning

confidence: 99%

“…We evaluated the performance of the method by predicting the missing head or tail entities in triples. We tested the performance of SP-TAG with two representative methods TransE and RotatE and compared it [24] and results of [ † †] are taken from reference [36].…”

Section: Link Predictionmentioning

confidence: 99%

“…Models that integrate text information include DKRL [ 14 ] and Joint [ 32 ], which use a continuous bag of words and CNN for text encoding; STKRL [ 33 ], which uses an RNN to obtain text sequence information; EDGE [ 34 ] and AATE [ 35 ], which are based on the bidirectional long short-term memory network; TA-ConvKB [ 36 ], which uses bidirectional short and long term memory network with attention to encode the text. The text- and structure-based representations are generally combined when calculating the score functions.…”

Section: Related Workmentioning

confidence: 99%

“… Best results are in bold and the second best results are italics. Results of [†] are taken from reference [ 24 ] and results of [††] are taken from reference [ 36 ]. Other results come from the corresponding original papers.…”

Section: Figurementioning

confidence: 99%

See 3 more Smart Citations

Representation Learning Method with Semantic Propagation on Text-Augmented Knowledge Graphs

Wang

Zhou

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Knowledge graph representation learning aims to provide accurate entity and relation representations for tasks such as intelligent question answering and recommendation systems. Existing representation learning methods, which only consider triples, are not sufficiently accurate, so some methods use external auxiliary information such as text, type, and time to improve performance. However, they often encode this information independently, which makes it challenging to fully integrate this information with the knowledge graph at a semantic level. In this study, we propose a method called SP-TAG, which realizes the semantic propagation on text-augmented knowledge graphs. Specifically, SP-TAG constructs a text-augmented knowledge graph by extracting named entities from text descriptions and connecting them with the corresponding entities. Then, SP-TAG uses a graph convolutional network to propagate semantic information between the entities and new named entities so that the text and triple structure are fully integrated. The results of experiments on multiple benchmark datasets show that SP-TAG attains competitive performance. When the number of training samples is limited, SP-TAG maintains its high performance, verifying the importance of text augmentation and semantic propagation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Link Predictionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Figurementioning

confidence: 99%

See 2 more Smart Citations

Representation Learning Method with Semantic Propagation on Text-Augmented Knowledge Graphs

Wang

Zhou

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…On a wider scope, instead of focusing on explaining existing architectures, there are approaches dealing with explainable-by-design machine learning methods. To better align the input features, [20], [21] suggest replacing the linear mapping of network with non-linear operators. Inspired by human recognition system, several works aim to quantify and prototype visual input according to the basic semantic units to integrate the interpretability to model structure [22], [23].…”

Section: Explaining Neural Networkmentioning

confidence: 99%

On Neuron Activation Pattern and Applications

Jiang,

Angelov,

Kangin

et al. 2024

Preprint

View full text Add to dashboard Cite

As various deep learning applications have been deployed in diverse areas, the explainability of neural networks is becoming increasingly important in the research field. Besides being desirable on its own account, explainability also often helps further improve performance of deep learning models. In this work, we introduce float neurons and fixed neurons to describe the neuron-level stability in a network based on the activation pattern of neurons on given input. With the proposed concept, we quantify the expressive ability and robustness of a neural network with a neuron entropy metric and illustrate their relationship by decomposing the computational graph of a neural network. We find theoretically that networks with better generalization have more diverse activation patterns across the input space, which results in a higher neuron entropy globally. On the other hand, the prediction of neural networks is prone to be affected by perturbation when there are locally more float neurons, which respond with additional impulses to local stimuli. Empirically, we show that the proposed analytical framework can be applied to downstream applications, including network pruning and randomized smoothing of network prediction.

show abstract