Differences

This shows you the differences between two versions of the page.

--- nlp:entity_linking [2021/10/26 08:24] – jmflanig
+++ nlp:entity_linking [2025/06/06 23:29] (current) – jmflanig
@@ Line 24: / Line 24: @@
   * [[https://www.aclweb.org/anthology/2020.emnlp-main.630.pdf|Botha et al 2020 - Entity Linking in 100 Languages]]
   * [[https://arxiv.org/pdf/2101.09969.pdf|Ravi et al 2021 - CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata]]
+==== Joint NER + EL ====
+  * [[https://aclanthology.org/P19-2026.pdf|Martins et al 2019 - Joint Learning of Named Entity Recognition and Entity Linking]]
 ==== Evaluation ====
@@ Line 31: / Line 34: @@
   * [[https://www.aclweb.org/anthology/2021.naacl-industry.4.pdf|Shang et al 2021 - Entity Resolution in Open-domain Conversations]]
-===== Name Dictionaries and Candidate Entities =====
+===== Candidate Entities =====
 Most EL systems use a "name dictionary" or "alias table," which is a list from strings to candidate entities they might refer to.  These are usually created using rule-based heuristics, such as running a string edit distance between entities in the knowledge graph and the train, dev and test set text beforehand (this is too slow for an online system).  The papers in this section describe methods of finding candidate entities (and perhaps also linking them at the same time).
-  * [[https://arxiv.org/pdf/1909.10506.pdf|Gillick et al 2019 - Learning Dense Representations for Entity Retrieval]]
+  * [[https://arxiv.org/pdf/1912.01070.pdf|Bansal et al 2019 - Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision]] "Candidate generation" section talks about using string-edit distance for candidate entities.
+  * [[https://arxiv.org/pdf/1909.10506.pdf|Gillick et al 2019 - Learning Dense Representations for Entity Retrieval]] Uses dense representations to retrieve candidate entities
 ===== Datasets =====