Fine-Grained Entity Typing for Domain Independent Entity Linking

TL;DR

This paper presents a domain-independent entity linking approach that models fine-grained entity properties using Wikipedia data, improving generalization and performance on unseen datasets.

Contribution

The authors introduce a large inventory of entity types from Wikipedia and a typing-based linking method that outperforms prior models in domain-independent scenarios.

Findings

Outperforms prior domain-independent entity linking systems on CoNLL-YAGO.

Generalizes better than neural models on unseen mention-entity pairs.

Uses large-scale Wikipedia-derived entity types for robust disambiguation.

Abstract

Neural entity linking models are very powerful, but run the risk of overfitting to the domain they are trained in. For this problem, a domain is characterized not just by genre of text but even by factors as specific as the particular distribution of entities, as neural models tend to overfit by memorizing properties of frequent entities in a dataset. We tackle the problem of building robust entity linking models that generalize effectively and do not rely on labeled entity linking data with a specific entity distribution. Rather than predicting entities directly, our approach models fine-grained entity properties, which can help disambiguate between even closely related entities. We derive a large inventory of types (tens of thousands) from Wikipedia categories, and use hyperlinked mentions in Wikipedia to distantly label data and train an entity typing model. At test time, we classify a mention with this typing model and use soft type predictions to link the mention to the most similar candidate entity. We evaluate our entity linking system on the CoNLL-YAGO dataset (Hoffart et al., 2011) and show that our approach outperforms prior domain-independent entity linking systems. We also test our approach in a harder setting derived from the WikilinksNED dataset (Eshel et al., 2017) where all the mention-entity pairs are unseen during test time. Results indicate that our approach generalizes better than a state-of-the-art neural model on the dataset.