Entity Enabled Relation Linking

Pan, Jeff Z.; Mei, Zhang; Singh, K. M.; Harmelen, Frank van; Gu, Jinguang; Zhang, Zhi

doi:10.1007/978-3-030-30793-6_30

Cited by 18 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relation linking has been important for various NLP tasks such as semantic parsing, knowledge graph induction (Gardent et al, 2017;Chen et al, 2021;Rossiello et al, 2022;Lin et al, 2020) and knowledge base question answering (Rossiello et al, 2021;Kapanipathi et al, 2020;Neelam et al, 2022). Prior to the surge of generative models, relation linking was addressed either by graph traversal based (Pan et al, 2019;Dubey et al, 2018) or by linguistic-features based methodologies (Sakor et al, 2019a,b;Lin et al, 2020). Several learning based approaches to relation linking have been proposed (Mihindukulasooriya et al, 2020;Yu et al, 2017;Bornea et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

Self-Supervised Rule Learning to Link Text Segments to Relational Elements of Structured Knowledge

Ikbal,

Sharma,

Karanam

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

We present a neuro-symbolic approach to selflearn rules that serve as interpretable knowledge to perform relation linking in knowledge base question answering systems. These rules define natural language text predicates as a weighted mixture of knowledge base paths. The weights learned during training effectively serve the mapping needed to perform relation linking. We use popular masked training strategy to self-learn the rules. A key distinguishing aspect of our work is that the masked training operate over logical forms of the sentence instead of their natural language text form. This offers opportunity to extract extended context information from the structured knowledge source and use that to build robust and human readable rules. We evaluate accuracy and usefulness of such learned rules by utilizing them for prediction of missing kinship relation in CLUTRR dataset and relation linking in a KBQA system using SWQ-WD dataset. Results demonstrate the effectiveness of our approach -its generalizability, interpretability and ability to achieve an average performance gain of 17% on CLUTRR dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-Supervised Rule Learning to Link Text Segments to Relational Elements of Structured Knowledge

Ikbal,

Sharma,

Karanam

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

show abstract

“…Figure 1. Entity type knowledge plays a key role in various natural language processing related tasks, such as entity and relation linking (Gupta et al, 2017;Pan et al, 2019), knowledge graph completion (Peng et al, 2022;Niu et al, 2022;Wiharja et al, 2020) answering (Hu et al, 2022b;Chen et al, 2019;Hu et al, 2023), and relation extraction . However, one cannot always have access to this kind of knowledge as KGs are inevitably incomplete (Zhu et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs

Hu,

Basulto,

Xiang

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Knowledge graph entity typing (KGET) aims at inferring plausible types of entities in knowledge graphs. Existing approaches to KGET focus on how to better encode the knowledge provided by the neighbors and types of an entity into its representation. However, they ignore the semantic knowledge provided by the way in which types can be clustered together. In this paper, we propose a novel method called Multi-view Contrastive Learning for knowledge graph Entity Typing (MCLET), which effectively encodes the coarse-grained knowledge provided by clusters into entity and type embeddings. MCLET is composed of three modules: i) Multi-view Generation and Encoder module, which encodes structured information from entity-type, entity-cluster and cluster-type views; ii) Cross-view Contrastive Learning module, which encourages different views to collaboratively improve view-specific representations of entities and types; iii) Entity Typing Prediction module, which integrates multi-head attention and a Mixture-of-Experts strategy to infer missing entity types. Extensive experiments show the strong performance of MCLET compared to the state-of-the-art.

show abstract

“…A knowledge graph (KG) (Pan et al, 2016) is a multi-relational graph encoding factual knowledge, with the form (h, r, t) where h, t are the head and tail entities connected via the relation r. In this paper, we consider KGs with minimal schema information, i.e., those containing entity type assertions, as the only schema information, of the form (e, has_type, c) stating that the entity e has type c; e.g., to capture that Barack Obama has type President. Entity type knowledge is widely used in NLP tasks, e.g., in relation extraction (Liu et al, 2014), entity and relation linking (Gupta et al, 2017;Pan et al, 2019), question answering (ElSahar et al, 2018;Hu et al, 2022), and finegrained entity typing on text (Onoe et al, 2021;Qian et al, 2021;. However, entity types are far from complete, since in real-world applications they are continuously emerging.…”

Section: Introductionmentioning

confidence: 99%

Transformer-based Entity Typing in Knowledge Graphs

Hu¹,

Gutiérrez-Basulto²,

Zhiliang³

et al. 2022

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We investigate the knowledge graph entity typing task which aims at inferring plausible entity types. In this paper, we propose a novel Transformer-based Entity Typing (TET) approach, effectively encoding the content of neighbors of an entity. More precisely, TET is composed of three different mechanisms: a local transformer allowing to infer missing types of an entity by independently encoding the information provided by each of its neighbors; a global transformer aggregating the information of all neighbors of an entity into a single long sequence to reason about more complex entity types; and a context transformer integrating neighbors content based on their contribution to the type inference through information exchange between neighbor pairs. Furthermore, TET uses information about class membership of types to semantically strengthen the representation of an entity. Experiments on two real-world datasets demonstrate the superior performance of TET compared to the state-of-the-art.

show abstract

Entity Enabled Relation Linking

Cited by 18 publications

References 30 publications

Self-Supervised Rule Learning to Link Text Segments to Relational Elements of Structured Knowledge

Self-Supervised Rule Learning to Link Text Segments to Relational Elements of Structured Knowledge

Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs

Transformer-based Entity Typing in Knowledge Graphs

Contact Info

Product

Resources

About