Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912230193233920 |
|---|---|
| author | Yoon, Soojin Ko, Sungho Kim, Tongyoung Kang, SeongKu Yeo, Jinyoung Lee, Dongha |
| author_facet | Yoon, Soojin Ko, Sungho Kim, Tongyoung Kang, SeongKu Yeo, Jinyoung Lee, Dongha |
| contents | Cross-lingual entity alignment (EA) enables the integration of multiple knowledge graphs (KGs) across different languages, providing users with seamless access to diverse and comprehensive knowledge. Existing methods, mostly supervised, face challenges in obtaining labeled entity pairs. To address this, recent studies have shifted towards self-supervised and unsupervised frameworks. Despite their effectiveness, these approaches have limitations: (1) Relation passing: mainly focusing on the entity while neglecting the semantic information of relations, (2) Isomorphic assumption: assuming isomorphism between source and target graphs, which leads to noise and reduced alignment accuracy, and (3) Noise vulnerability: susceptible to noise in the textual features, especially when encountering inconsistent translations or Out-of-Vocabulary (OOV) problems. In this paper, we propose ERAlign, an unsupervised and robust cross-lingual EA pipeline that jointly performs Entity-level and Relation-level Alignment by neighbor triple matching strategy using semantic textual features of relations and entities. Its refinement step iteratively enhances results by fusing entity-level and relation-level alignments based on neighbor triple matching. The additional verification step examines the entities' neighbor triples as the linearized text. This Align-then-Verify pipeline rigorously assesses alignment results, achieving near-perfect alignment even in the presence of noisy textual features of entities. Our extensive experiments demonstrate that the robustness and general applicability of ERAlign improved the accuracy and effectiveness of EA tasks, contributing significantly to knowledge-oriented applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts Yoon, Soojin Ko, Sungho Kim, Tongyoung Kang, SeongKu Yeo, Jinyoung Lee, Dongha Computation and Language Artificial Intelligence Cross-lingual entity alignment (EA) enables the integration of multiple knowledge graphs (KGs) across different languages, providing users with seamless access to diverse and comprehensive knowledge. Existing methods, mostly supervised, face challenges in obtaining labeled entity pairs. To address this, recent studies have shifted towards self-supervised and unsupervised frameworks. Despite their effectiveness, these approaches have limitations: (1) Relation passing: mainly focusing on the entity while neglecting the semantic information of relations, (2) Isomorphic assumption: assuming isomorphism between source and target graphs, which leads to noise and reduced alignment accuracy, and (3) Noise vulnerability: susceptible to noise in the textual features, especially when encountering inconsistent translations or Out-of-Vocabulary (OOV) problems. In this paper, we propose ERAlign, an unsupervised and robust cross-lingual EA pipeline that jointly performs Entity-level and Relation-level Alignment by neighbor triple matching strategy using semantic textual features of relations and entities. Its refinement step iteratively enhances results by fusing entity-level and relation-level alignments based on neighbor triple matching. The additional verification step examines the entities' neighbor triples as the linearized text. This Align-then-Verify pipeline rigorously assesses alignment results, achieving near-perfect alignment even in the presence of noisy textual features of entities. Our extensive experiments demonstrate that the robustness and general applicability of ERAlign improved the accuracy and effectiveness of EA tasks, contributing significantly to knowledge-oriented applications. |
| title | Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.15588 |