Impact of translation on named-entity recognition in radiology texts

Abstract

Radiology reports describe the results of radiography procedures and have the potential of being a useful source of information which can bring benefits to health care systems around the world. One way to automatically extract information from the reports is by using Text Mining tools. The problem is that these tools are mostly developed for English and reports are usually written in the native language of the radiologist, which is not necessarily English. This creates an obstacle to the sharing of Radiology information between different communities. This work explores the solution of translating the reports to English before applying the Text Mining tools, probing the question of what translation approach should be used. We created MRRAD (Multilingual Radiology Research Articles Dataset), a parallel corpus of Portuguese research articles related to Radiology and a number of alternative translations (human, automatic and semi-automatic) to English. This is a novel corpus which can be used to move forward the research on this topic. Using MRRAD we studied which kind of automatic or semi-automatic translation approach is more effective on the Named-entity recognition task of finding RadLex terms in the English version of the articles. Considering the terms extracted from human translations as our gold standard, we calculated how similar to this standard were the terms extracted using other translations. We found that a completely automatic translation approach using Google leads to F-scores (between 0.861 and 0.868, depending on the extraction approach) similar to the ones obtained through a more expensive semi-automatic translation approach using Unbabel (between 0.862 and 0.870). To better understand the results we also performed a qualitative analysis of the type of errors found in the automatic and semi-automatic translations. Database URL: https://github.com/lasigeBioTM/MRRAD

Assessing Public Metabolomics Metadata, Towards Improving Quality

“…Ontologies, therefore, offer several benefits: e.g. automatic methods can leverage on the meaning behind metadata to detect related resources and even compile lists of resources on a given subject, organise them in meaningful groups and categories, and ultimately deal with integrating resources from disparate sources and even using different languages [14]. Another example is Google’s knowledge graph [15], [16], which enriches a search result by providing disambiguation, topic summary, and links to related resources.…”

Identifying Human Phenotype Terms by Combining Machine Learning and Validation Rules

“…It would also be interesting to apply phenotypic similarity to identify potential misannotations that are not semantically related to the entities found in the text [ 21 ]. Since electronic health records contain HPO terms, an exciting challenge would be to assess the performance of IHP in a multilingual corpus [ 22 ] and how it could help us to represent their knowledge using linked data technologies [ 23 ].…”

Essential Elements of Natural Language Processing: What the Radiologist Should Know

“…Other examples of medical ontologies include the Unified Medical Language System and Medical Subject Headings. Ontologies have been successfully used in NER algorithms explicitly designed for the medical domain (29,30).…”