Named entity normalization in user generated content

Abstract

Named entity recognition is important for semantically oriented retrieval tasks, such as question answering, entity retrieval, biomedical retrieval, trend detection, and event and entity tracking. In many of these tasks it is important to be able to accurately normalize the recognized entities, i.e., to map surface forms to unambiguous references to real world entities. Within the context of structured databases, this task (known as record linkage and data de-duplication) has been a topic of active research for more than five decades. For edited content, such as news articles, the named entity normalization (NEN) task is one that has recently attracted considerable attention. We consider the task in the challenging context of user generated content (UGC), where it forms a key ingredient of tracking and media-analysis systems.A baseline NEN system from the literature (that normalizes surface forms to Wikipedia pages) performs considerably worse on UGC than on edited news: accuracy drops from 80% to 65% for a Dutch language data set and from 94% to 77% for English. We identify several sources of errors: entity recognition errors, multiple ways of referring to the same entity and ambiguous references.To address these issues we propose five improvements to the baseline NEN algorithm, to arrive at a language independent NEN system that achieves overall accuracy scores of 90% on the English data set and 89% on the Dutch data set. We show that each of the improvements contributes to the overall score of our improved NEN algorithm, and conclude with an error analysis on both Dutch and English language UGC. The NEN system is computationally efficient and runs with very modest computational requirements.

Context & Semantics in News & Web Search

“…Entity linking has been applied to many different specific domains. Jijkoun et al [106] studied this as an entity normalization task in blogs and comments. He et al [94] showed that applying entity linking to radiology reports did not yield satisfactory results and propose a sequential labeling approach, with syntactic features.…”

Automatically embedding newsworthy links to articles: From implementation to evaluation

“…It has recently gained new interest, primarily within the context of Wikipedia, looking at cross-referencing documents [20,24,28], missing link detection [11], automatic approaches for hyperlinking [12,15], automatically linking documents to encyclopaedic knowledge [16,23,26], and entity linking augmented with human intelligence [9]. Link generation approaches are also used in disambiguation tasks [6,8,18]. Many of these works are not directly comparable to ours because of different aims and a reliance on properties specific to Wikipedia.…”

A systematic review of named entity recognition in biomedical texts

“…This problem is treated as disambiguation. (d) Normalization: despite Hakenberg definition of normalization as a disambiguation procedure [10], in the present work, normalization is understood as the process of relating NEs mentioned in the texts to entries in databases structured with biological data, such as ontologies or genetic sequencing databases [11][12][13]. (e) Recognition, identification, or extraction: the terms recognition, identification, and extraction are treated as synonyms in this taxonomy.…”