Learning Dense Representations for Entity Retrieval
We show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate entities are retrieved by approximate nearest neighbor search. Unlike prior work, this setup does not rely on an alias table followed by a re-ranker, and is thus the first fully learned entity retrieval model. We show that our dual encoder, trained using only anchor-text links in Wikipedia, outperforms discrete alias table and BM25 baselines, and is competitive with the best comparable results on the standard TACKBP-2010 dataset. In addition, it can retrieve candidates extremely fast, and generalizes well to a new dataset derived from Wikinews. On the modeling side, we demonstrate the dramatic value of an unsupervised negative mining algorithm for this task.
Code (0)
등록된 구현이 없습니다.
Tasks
Entity LinkingEntity RetrievalRetrievalSimilar Papers 제목 키워드 기반
MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering
We describe our two-stage system for the Multilingual Information Access (MIA) 2022 Shared Task on Cross-Lingual Open-Retrieval Question Answering. The first stage consists of multilingual passage retrieval with a hybrid…
Cross-Lingual Question AnsweringDecoderLanguage ModelingLanguage Modelling+3Early Stage Sparse Retrieval with Entity Linking
Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection.…
Entity LinkingInformation RetrievalRetrievalInformation Retrieval with Entity Linking
Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection.…
Entity LinkingInformation RetrievalRetrievalNER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Retrieval, a variant of Named Entity Recognition (NER), where the types of interest are not provided in advance, and a user-defined type d…
Semantic Driven Fielded Entity Retrieval
A common approach for knowledge-base entity search is to consider an entity as a document with multiple fields. Models that focus on matching query terms in different fields are popular choices for searching such entity …
Entity RetrievalRe-RankingRetrieval