Cross-lingual Entity Alignment with Incidental Supervision

Abstract

Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagespecific KGs that refer to the same real-world object. Such methods are often hindered by the insufficiency of seed alignment provided between KGs. Therefore, we propose an incidentally supervised model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental supervision signals from text. JEANS first deploys an entity grounding process to combine each KG with the monolingual text corpus. Then, two learning processes are conducted: (i) an embedding learning process to encode the KG and text of each language in one embedding space, and (ii) a selflearning based alignment learning process to iteratively induce the matching of entities and that of lexemes between embeddings. Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision, and significantly outperforms state-of-the-art methods that solely rely on internal information of KGs.

arXiv commentEACL 2021

References in corpus (15)

• Efficient Estimation of Word Representations in Vector Space
• On the Convergence of Adam and Beyond
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Poincaré GloVe: Hyperbolic Word Embeddings
• How multilingual is Multilingual BERT?
• PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• Incidental Supervision: Moving beyond Supervised Learning
• Teaching Pretrained Models with Commonsense Reasoning: A Preliminary KB-Based Approach
• Word Embeddings for Entity-annotated Texts
• DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension