Multi-Task Learning and Improved TextRank for Knowledge Graph Completion

Tian, Hao; Zhang, Xiaoxiong; Wang, Yuhan; Zeng, Daojian

doi:10.3390/e24101495

Cited by 4 publications

(6 citation statements)

References 29 publications

(47 reference statements)

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%

See 1 more Smart Citation

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%

“… 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%

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

“…Domain-generic ontologies like the CIDOC Conceptual Reference Model (CIDOC CRM), 2 the Historical Context Ontology (HiCO) 3 and the Europeana Data Model (EDM), 4 have been used for information integration, exchange, sharing, and reuse in the CH domain. Project-applied ontologies, such as ArCo ontology (ArCo) 5 and CrossCult ontology (CrossCult), 6 have been developed for specific projects. Top-level ontologies like Friend of a Friend (FOAF), 7 GeoNames, 8 Visual Representation Ontology (VRO), 9 Time ontology (Time), 10 and the Ontology for Media 1 https:// pro.…”

Section: Related Workmentioning

confidence: 99%

“…DKGs refine, extract, correlate, and integrate data related to ICH projects, helping audiences interpret and appreciate the essence of ICH [3][4][5]. Currently, the primary focus of ICH project DKGs is to effectively organize information resources and link multi-source heterogeneous data [6]. Examples include the Europeana project [7], ICHPEDIA project [8], and I-Treasures project [9].…”

Section: Introductionmentioning

confidence: 99%

A study on the construction of knowledge graph of Yunjin video resources under productive conservation

Yuan

et al. 2023

Herit Sci

View full text Add to dashboard Cite

Nanjing Yunjin, a highly representative Chinese silk weaving handicraft, was included in the Representative List of Intangible Cultural Heritage of Humanity in 2009. However, due to modern silk weaving technology advancements, aesthetic style evolution, and inadequate public recognition of Yunjin culture, the art faces a decline in market recognition and practitioners, posing a risk to its preservation. Addressing this issue necessitates product innovation, efficient knowledge storage, management, and utilization, and enhancing public cultural identity for Yunjin. Following the government’s “productive conservation” concept for intangible cultural heritage (ICH) projects in the handicraft category, this study uses Yunjin video resources as the primary data source. It constructs a domain knowledge graph (DKG) using an ontological approach to effectively and systematically preserve Yunjin knowledge. Furthermore, the study leverages Neo4j network topology to reveal intricate and diverse relationships within Yunjin knowledge, uncovering rich cultural connotations. Lastly, Cypher is employed for semantic queries, graph visualization, and domain expert evaluation. Evaluation results indicate that the constructed Yunjin DKG meets quality standards, supporting the development of products that align with market aesthetics while preserving Yunjin’s intrinsic cultural values. This approach fosters a complementary relationship between economic benefits and ICH. Additionally, the Yunjin DKG application presents a technical path for knowledge interconnection, integration, and discovery within ICH projects in the handicraft category.

show abstract

“…Entity–relationship extraction means to extract entity relationships from unstructured text [ 1 , 2 ] and convert them into structured data by analyzing unstructured text. Entity–relationship extraction is very important for building knowledge graphs and question-answering systems [ 3 ], and information retrieval tasks [ 4 , 5 ] play a crucial role [ 6 ]. The entity–relationship triple is one of the basic representation methods of entity relationships.…”

Section: Introductionmentioning

confidence: 99%

A Joint Extraction Model for Entity Relationships Based on Span and Cascaded Dual Decoding

Tao

Sun

Zhang

2023

Entropy

View full text Add to dashboard Cite

The entity–relationship joint extraction model plays a significant role in entity relationship extraction. The existing entity–relationship joint extraction model cannot effectively identify entity–relationship triples in overlapping relationships. This paper proposes a new joint entity–relationship extraction model based on the span and a cascaded dual decoding. The model includes a Bidirectional Encoder Representations from Transformers (BERT) encoding layer, a relational decoding layer, and an entity decoding layer. The model first converts the text input into the BERT pretrained language model into word vectors. Then, it divides the word vectors based on the span to form a span sequence and decodes the relationship between the span sequence to obtain the relationship type in the span sequence. Finally, the entity decoding layer fuses the span sequences and the relationship type obtained by relation decoding and uses a bi-directional long short-term memory (Bi-LSTM) neural network to obtain the head entity and tail entity in the span sequence. Using the combination of span division and cascaded double decoding, the overlapping relations existing in the text can be effectively identified. Experiments show that compared with other baseline models, the F1 value of the model is effectively improved on the NYT dataset and WebNLG dataset.

show abstract

Multi-Task Learning and Improved TextRank for Knowledge Graph Completion

Cited by 4 publications

References 29 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

A study on the construction of knowledge graph of Yunjin video resources under productive conservation

A Joint Extraction Model for Entity Relationships Based on Span and Cascaded Dual Decoding

Contact Info

Product

Resources

About