CLApr 27, 2018

Improving Entity Linking by Modeling Latent Relations between Mentions

arXiv:1804.10637v11145 citations
Originality Highly original
AI Analysis

This improves entity linking for NLP applications by introducing a novel unsupervised relational approach, though it is incremental over existing methods.

The paper tackles the problem of entity linking by modeling latent relations between mentions as unsupervised variables within a neural model, achieving state-of-the-art scores on the AIDA-CoNLL benchmark and faster training convergence.

Entity linking involves aligning textual mentions of named entities to their corresponding entries in a knowledge base. Entity linking systems often exploit relations between textual mentions in a document (e.g., coreference) to decide if the linking decisions are compatible. Unlike previous approaches, which relied on supervised systems or heuristics to predict these relations, we treat relations as latent variables in our neural entity-linking model. We induce the relations without any supervision while optimizing the entity-linking system in an end-to-end fashion. Our multi-relational model achieves the best reported scores on the standard benchmark (AIDA-CoNLL) and substantially outperforms its relation-agnostic version. Its training also converges much faster, suggesting that the injected structural bias helps to explain regularities in the training data.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes