Advancements in Complex Knowledge Graph Question Answering: A Survey

Song, Yiqing; Li, Wenfa; Dai, Guiren; Shang, Xinna

doi:10.3390/electronics12214395

Cited by 6 publications

(8 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… An example from dataset DocRED. Intra-sentential and inter-sentential are marked with blue and red lines, respectively [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 ]. …”

Section: Figurementioning

confidence: 99%

“… Examples of three relation reasoning paths and pre-coreference-resolution. Note that after pre-coreference-resolution, the coreference reasoning paths would be converted into intra-sentential relation paths [ 1 , 2 , 3 , 7 ]. …”

Section: Figurementioning

confidence: 99%

“…Case 1 involves the coreference reasoning path. Cases 2 and 3 involve the relational logical inference path [ 1 , 2 , 7 ].…”

Section: Figurementioning

confidence: 99%

“…Document-level relation extraction (DocRE) is defined as extracting all relationships between entities in multiple sentences of a document, which plays a critical role in many natural language processing tasks, such as knowledge graph construction, knowledge discovery, and knowledge-based question answering [1][2][3]. Compared to sentence-level relation extraction [4], DocRE is more challenging and harder to deal with for three main reasons: (1) Each entity in DocRE may have multiple mentions distributed across multiple sentences; (2) Relationships in the DocRE setting may span multiple sentences; (3) Logical reasoning is required to identify many complex relationships.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Chen,

Shi

2024

Entropy

View full text Add to dashboard Cite

Recent years have seen a rise in interest in document-level relation extraction, which is defined as extracting all relations between entities in multiple sentences of a document. Typically, there are multiple mentions corresponding to a single entity in this context. Previous research predominantly employed a holistic representation for each entity to predict relations, but this approach often overlooks valuable information contained in fine-grained entity mentions. We contend that relation prediction and inference should be grounded in specific entity mentions rather than abstract entity concepts. To address this, our paper proposes a two-stage mention-level framework based on an enhanced heterogeneous graph attention network for document-level relation extraction. Our framework employs two different strategies to model intra-sentential and inter-sentential relations between fine-grained entity mentions, yielding local mention representations for intra-sentential relation prediction and global mention representations for inter-sentential relation prediction. For inter-sentential relation prediction and inference, we propose an enhanced heterogeneous graph attention network to better model the long-distance semantic relationships and design an entity-coreference path-based inference strategy to conduct relation inference. Moreover, we introduce a novel cross-entropy-based multilabel focal loss function to address the class imbalance problem and multilabel prediction simultaneously. Comprehensive experiments have been conducted to verify the effectiveness of our framework. Experimental results show that our approach significantly outperforms the existing methods.

show abstract

“… An example from dataset DocRED. Intra-sentential and inter-sentential are marked with blue and red lines, respectively [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 ]. …”

Section: Figurementioning

confidence: 99%

Section: Figurementioning

confidence: 99%

“…Case 1 involves the coreference reasoning path. Cases 2 and 3 involve the relational logical inference path [ 1 , 2 , 7 ].…”

Section: Figurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Chen,

Shi

2024

Entropy

View full text Add to dashboard Cite

show abstract

“…With the rapid development of the Semantic Web, various types of knowledge bases (KBs) have been proposed, such as DBpedia [7] , Wikidata [8], and Free-Base [9]. Knowledge Base Question Answering (KBQA) systems, which have garnered considerable attention from researchers, enable users-particularly those without programming expertise-to effortlessly interact with Knowledge Bases [10][11][12][13]. Central to KBQA is Complex Question Answering (CQA) which navigates queries containing multiple subjects, compound relations, or numerical operations, and is vital in applications like Apple's Siri and Microsoft's Cortana [14].…”

Section: Introductionmentioning

confidence: 99%

Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets

Qi,

Su,

Guo

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Generating SPARQL queries from natural language questions is challenging in Knowledge Base Question Answering (KBQA) systems. The current state-of-the-art models heavily rely on fine-tuning pretrained models such as T5. However, these methods still encounter critical issues such as triple-flip errors (e.g., (subject, relation, object) is predicted as (object, relation, subject)). To address this limitation, we introduce TSET (Triplet Structure Enhanced T5), a model with a novel pretraining stage positioned between the initial T5 pretraining and the fine-tuning for the Text-to-SPARQL task. In this intermediary stage, we introduce a new objective called Triplet Structure Correction (TSC) to train the model on a SPARQL corpus derived from Wikidata. This objective aims to deepen the model’s understanding of the order of triplets. After this specialized pretraining, the model undergoes fine-tuning for SPARQL query generation, augmenting its query-generation capabilities. We also propose a method named “semantic transformation” to fortify the model’s grasp of SPARQL syntax and semantics without compromising the pre-trained weights of T5. Experimental results demonstrate that our proposed TSET outperforms existing methods on three well-established KBQA datasets: LC-QuAD 2.0, QALD-9 plus, and QALD-10, establishing a new state-of-the-art performance (95.0% F1 and 93.1% QM on LC-QuAD 2.0, 75.85% F1 and 61.76% QM on QALD-9 plus, 51.37% F1 and 40.05% QM on QALD-10).

show abstract

Anomaly detection based on a deep graph convolutional neural network for reliability improvement

Xu,

Hu,

Qie

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

Effective anomaly detection in power grid engineering is essential for ensuring the reliability of dispatch and operation. Traditional anomaly detection methods based on manual review and expert experience cannot be adapted to the current rapid increases in project data. In this work, to address this issue, knowledge graph technology is used to build an anomaly detection dataset. Considering the over-smoothing problem associated with multi-level GCN networks, a deep skip connection framework for anomaly detection on attributed networks called DIET is proposed for anomaly detection on ultra-high voltage (UHV) projects. Furthermore, a distance-based object function is added to the conventional object function, which gives DIET the ability to process multiple attributes of the same type. Several comparative experiments are conducted using five state-of-the-art algorithms. The results of the receiver operating characteristic with the area under the curve (ROC-AUC) indicator show a 12% minimum improvement over other methods. Other evaluation indicators such as precision@K and recall@K indicate that DIET can achieve a better detection rate with less ranking. To evaluate the feasibility of the proposed model, a parameter analysis of the number of GCN layers is also performed. The results show that relatively few layers are needed to achieve good results with small datasets.

show abstract

Advancements in Complex Knowledge Graph Question Answering: A Survey

Cited by 6 publications

References 71 publications

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets

Anomaly detection based on a deep graph convolutional neural network for reliability improvement

Contact Info

Product

Resources

About