Improving Entity Linking by Modeling Latent Relations between Mentions
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 (2)
Tasks
Entity LinkingSimilar Papers 제목 키워드 기반
LATTE: Latent Type Modeling for Biomedical Entity Linking
Entity linking is the task of linking mentions of named entities in natural language text, to entities in a curated knowledge-base. This is of significant importance in the biomedical domain, where it could be used to se…
Entity DisambiguationEntity LinkingVocal Bursts Type PredictionImproving Entity Linking by Modeling Latent Entity Type Information
Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility. Ho…
Entity DisambiguationEntity EmbeddingsEntity LinkingVocal Bursts Type Prediction+1Clustering-based Inference for Biomedical Entity Linking
Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unsee…
ClusteringEntity LinkingDGCN Based Solution for Entity Linking on Visual Rich Document
Various works on entity extraction on visual rich document (VRD) have been done. However, few methods have been explored to handle entity linking problem. The difficulties come from the number of possible linking edges a…
Entity LinkingEntity Linking via Explicit Mention-Mention Coreference Modeling
Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions. In this paper, we present and empirically analyze a novel tra…
Entity LinkingRe-Ranking