Low-Rank Subspaces for Unsupervised Entity Linking
Akhil Arora, Alberto García-Durán, Robert West
Abstract
Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable entity linking method, EIGENTHEMES, that relies solely on the availability of entity names and a referent knowledge base. EIGENTHEMES exploits the fact that the entities that are truly mentioned in a document (the "gold entities") tend to form a semantically dense subset of the set of all candidate entities in the document. Geometrically speaking, when representing entities as vectors via some given embedding, the gold entities tend to lie in a low-rank subspace of the full embedding space. EIGENTHEMES identifies this subspace using the singular value decomposition and scores candidate entities according to their proximity to the subspace. On the empirical front, we introduce multiple strong baselines that compare favorably to (and sometimes even outperform) the existing state of the art. Extensive experiments on benchmark datasets from a variety of real-world domains showcase the effectiveness of our approach. * Research done while at EPFL. 𝐶 !! = Michael_Jordan_(basketball_player) 𝐶 !" = Michael_Jordan_(computer_scientist) 𝐶 !# = Mike_Jordan_(racing_driver) 𝐶 ! = Michael-Hakim_Jordan 𝐶 "! = Natural_Science 𝐶 "" = Applied_Science 𝐶 "# = Science_(album) 𝐶 " = Life_Science 𝐶 "% = Science_(journal)
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Related papers
- Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity LinkingTuan Manh Lai, Heng Ji, ChengXiang ZhaiACL Findings 2022 · 18 citations
- Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference ResolutionSeverine Verlinden, Klim Zaporojets, Johannes Deleu, Thomas Demeester et al.ACL Findings 2021 · 30 citations
- TENET: Joint Entity and Relation Linking with Coherence RelaxationXueling Lin, Lei Chen, Chaorui ZhangSIGMOD 2021 · 3 citations
- A Lightweight Neural Model for Biomedical Entity LinkingLihu Chen, Gaël Varoquaux, Fabian M. SuchanekAAAI 2021 · 39 citations
- Autoregressive Entity RetrievalNicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio PetroniICLR 2021 · 200 citations
