Annotating and recognising named entities in clinical notes

Abstract

This paper presents ongoing research in clinical information extraction. This work introduces a new genre of text which are not well-written, noise prone, ungrammatical and with much cryptic content. A corpus of clinical progress notes drawn form an Intensive Care Service has been manually annotated with more than 15000 clinical named entities in 11 entity types. This paper reports on the challenges involved in creating the annotation schema, and recognising and annotating clinical named entities. The information extraction task has initially used two approaches: a rule based system and a machine learning system using Conditional Random Fields (CRF). Different features are investigated to assess the interaction of feature sets and the supervised learning approaches to establish the combination best suited to this data set. The rule based and CRF systems achieved an F-score of 64.12% and 81.48% respectively.

Named Entity Recognition for Patent Documents Based on Conditional Random Fields

“…인식에 관한 연구를 하고 있다 [3,4]. 사전 조사 자질로는 용어 사전, 불용어, 약어, 조직명, 부처명, 항공사, 교육 기관 등에 서 이미 목록화된 자질을 사용한다. <true, 3, "the">, <false, 9, "president">, <false, 2, "of">, <true, 5, "apple">, <false, 4, "eats">, <false, 2, "an">, <false, 5, "apple"> …”

A Neural Layered Model for Nested Named Entity Recognition

“…This phenomenon is quite common in many domains (Alex et al, 2007;Byrne, 2007;Wang, 2009;Màrquez et al, 2007). However, much of the work on NER copes only with non-nested entities which are also called flat entities and neglects nested entities.…”

Proceedings of the COLING Workshop on Synchronic and Diachronic Approaches to Analyzing Technical Language

“…Ideal annotation should be accurate, thus requiring intensive knowledge and context awareness, and it should be automatic at the same time, since expert work is time consuming. Many efforts have been made in this field, from named entity recognition (NER) to information extraction (Ciravegna et al, 2004;Kiryakov et al, 2004), both in open domain (Uren et al, 2006;Cucerzan, 2007;Mihalcea and Csomai, 2007) and particular domains (Wang, 2009;Liu et al, 2011). Most cases of NER or information extraction focus on a small set of categories to be annotated, such as Person, Location, Organization, Misc, etc.…”