Cross-lingual Candidate Search for Biomedical Concept Normalization
This work addresses the problem of limited non-English resources for biomedical concept normalization, which is crucial for clinical NLP applications under privacy restrictions, though it is incremental as it builds on existing translation methods.
The paper tackled the challenge of biomedical concept normalization for non-English texts by proposing a cross-lingual candidate search using a character-based neural translation model trained on multilingual biomedical terminologies. The model outperformed most teams in CLEF eHealth evaluations on French data and performed similarly to commercial translators on multiple languages while being free and locally runnable.
Biomedical concept normalization links concept mentions in texts to a semantically equivalent concept in a biomedical knowledge base. This task is challenging as concepts can have different expressions in natural languages, e.g. paraphrases, which are not necessarily all present in the knowledge base. Concept normalization of non-English biomedical text is even more challenging as non-English resources tend to be much smaller and contain less synonyms. To overcome the limitations of non-English terminologies we propose a cross-lingual candidate search for concept normalization using a character-based neural translation model trained on a multilingual biomedical terminology. Our model is trained with Spanish, French, Dutch and German versions of UMLS. The evaluation of our model is carried out on the French Quaero corpus, showing that it outperforms most teams of CLEF eHealth 2015 and 2016. Additionally, we compare performance to commercial translators on Spanish, French, Dutch and German versions of Mantra. Our model performs similarly well, but is free of charge and can be run locally. This is particularly important for clinical NLP applications as medical documents underlay strict privacy restrictions.