End-to-End Neural Entity Linking

Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL 2018), pages 519–529 Brussels, Belgium, October 31 - November 1, 2018. c⃝2018 Association for Computational Linguistics 519 End-to-End Neural Entity Linking Nikolaos Kolitsas ∗ ETH Zürich nikos_kolitsas@hotmail.com Octavian-Eugen Ganea ∗ ETH Zürich octavian.ganea@inf.ethz.ch Thomas Hofmann ETH Zürich thomas.hofmann@inf.ethz.ch Abstract Entity Linking (EL) is an essential task for se- mantic text understanding and information ex- traction. Popular methods separately address the Mention Detection (MD) and Entity Dis- ambiguation (ED) stages of EL, without lever- aging their mutual dependency. We here pro- pose the first neural end-to-end EL system that jointly discovers and links entities in a text doc- ument. The main idea is to consider all possi- ble spans as potential mentions and learn con- textual similarity scores over their entity can- didates that are useful for both MD and ED decisions. Key components are context-aware mention embeddings, entity embeddings and a probabilistic mention - entity map, without demanding other engineered features. Empir- ically, we show that our end-to-end method significantly outperforms popular systems on the Gerbil platform when enough training data is available. Conversely, if testing datasets follow different annotation conventions com- pared to the training set (e.g. queries/ tweets vs news documents), our ED model coupled with a traditional NER system offers the best or second best EL accuracy. 1 Introduction and Motivation Towards the goal of automatic text understanding, machine learning models are expected to accurately extract potentially ambiguous mentions of enti- ties from a textual document and link them to a knowledge base (KB), e.g. Wikipedia or Freebase. Known as entity linking, this problem is an essen- tial building block for various Natural Language Processing tasks, e.g. automatic KB construction, question-answering, text summarization, or rela- tion extraction. An EL system typically performs two tasks: i) Mention Detection (MD) or Named Entity Recog- ∗Equal contribution. 1) MD may split a larger span into two mentions of less informative entities: B. Obama’s wife gave a speech [...] Federer’s coach [...] 2) MD may split a larger span into two mentions of incorrect entities: Obama Castle was built in 1601 in Japan. The Kennel Club is UK’s official kennel club. A bird dog is a type of gun dog or hunting dog. Romeo and Juliet by Shakespeare [...] Natural killer cells are a type of lymphocyte Mary and Max, the 2009 movie [...] 3) MD may choose a shorter span, referring to an incorrect entity: The Apple is played again in cinemas. The New York Times is a popular newspaper. 4) MD may choose a longer span, referring to an incorrect entity: Babies Romeo and Juliet were born hours apart. Table 1: Examples where MD may benefit from ED and viceversa. Each wrong MD decision (under- lined) can be avoided by proper context understand- ing. The correct spans are shown in blue. nition (NER) when restricted to named entities – extracts entity references in a raw textual input, and ii) Entity Disambiguation (ED) – links these spans to their …

Content truncated to 500 words