Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts

Abstract

Named entity recognition is a crucial component of biomedical natural language processing, enabling information extraction and ultimately reasoning over and knowledge discovery from text. Much progress has been made in the design of rule-based and supervised tools, but they are often genre and task dependent. As such, adapting them to different genres of text or identifying new types of entities requires major effort in re-annotation or rule development. In this paper, we propose an unsupervised approach to extracting named entities from biomedical text. We describe a stepwise solution to tackle the challenges of entity boundary detection and entity type classification without relying on any handcrafted rules, heuristics, or annotated data. A noun phrase chunker followed by a filter based on inverse document frequency extracts candidate entities from free text. Classification of candidate entities into categories of interest is carried out by leveraging principles from distributional semantics. Experiments show that our system, especially the entity classification step, yields competitive results on two popular biomedical datasets of clinical notes and biological literature, and outperforms a baseline dictionary match approach. Detailed error analysis provides a road map for future work.

Increasing papers’ discoverability with precise semantic labeling: The sci.AI publishing platform

“…This feature will be based on the (a) logs of the terms validation events and (b) statistical co-occurrences of the terms in all available texts. We expect that it will provide approximately 90% recognition rate, as reported by NN researchers [1,20]. Introduction of the NN prioritisation is expected to reduce cases of the necessary authors intervention to the reasonable minimum.…”

Biomedical Named Entity Recognition - a swift review

“…Shaodian Zhang et al [26] proposed unsupervised approach to overcome the challenges of entity boundary detection and entity type classification. Their method identified entities from raw text , leveraged existing terminology in lieu of task specific user defined rules or online information retrieval and added internal words using TF-IDF weights.…”

Bio Medical Named Entity Recognition Using Machine Learning Algorithms

“…Shaodian Zhang et al [12] gives possible improvements on the approach including nested NPs as candidates, better chunker for medical text, better domain representations, and improved IDF values of phrases. The paper gives solution to tackle the challenges of entity boundary detection and entity type classification.…”