Improving Zero-Shot Entity Retrieval through Effective Dense Representations

by   Eleni Partalidou, et al.

Entity Linking (EL) seeks to align entity mentions in text to entries in a knowledge-base and is usually comprised of two phases: candidate generation and candidate ranking. While most methods focus on the latter, it is the candidate generation phase that sets an upper bound to both time and accuracy performance of the overall EL system. This work's contribution is a significant improvement in candidate generation which thus raises the performance threshold for EL, by generating candidates that include the gold entity in the least candidate set (top-K). We propose a simple approach that efficiently embeds mention-entity pairs in dense space through a BERT-based bi-encoder. Specifically, we extend (Wu et al., 2020) by introducing a new pooling function and incorporating entity type side-information. We achieve a new state-of-the-art 84.28 on top-50 candidates on the Zeshel dataset, compared to the previous 82.06 the top-64 of (Wu et al., 2020). We report the results from extensive experimentation using our proposed model on both seen and unseen entity datasets. Our results suggest that our method could be a useful complement to existing EL approaches.


page 1

page 2

page 3

page 4


Zero-shot Entity Linking with Dense Entity Retrieval

We consider the zero-shot entity-linking challenge where each entity is ...

Entity Linking via Dual and Cross-Attention Encoders

Entity Linking has two main open areas of research: 1) generate candidat...

Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

We propose an autoregressive entity linking model, that is trained with ...

Medical Entity Linking using Triplet Network

Entity linking (or Normalization) is an essential task in text mining th...

RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering

Existing KBQA approaches, despite achieving strong performance on i.i.d....

Paraphrasing via Ranking Many Candidates

We present a simple and effective way to generate a variety of paraphras...

Low-rank Subspaces for Unsupervised Entity Linking

Entity linking is an important problem with many applications. Most prev...