xMEN: A Modular Toolkit for Cross-Lingual Medical Entity Normalization

TL;DR

xMEN is a modular, extensible toolkit that significantly improves cross-lingual medical entity normalization, especially in low-resource languages, by leveraging English aliases and trainable cross-encoders, and is publicly available for research use.

Contribution

The paper introduces xMEN, a novel modular toolkit that enhances multilingual medical entity normalization, particularly in low-resource settings, by combining candidate generation, cross-encoder ranking, and weak supervision techniques.

Findings

xMEN achieves state-of-the-art results across multiple multilingual benchmarks.

Weakly supervised cross-encoders perform well without target language training data.

The toolkit is compatible with existing frameworks and is openly accessible.

Abstract

Objective: To improve performance of medical entity normalization across many languages, especially when fewer language resources are available compared to English. Materials and Methods: We introduce xMEN, a modular system for cross-lingual medical entity normalization, which performs well in both low- and high-resource scenarios. When synonyms in the target language are scarce for a given terminology, we leverage English aliases via cross-lingual candidate generation. For candidate ranking, we incorporate a trainable cross-encoder model if annotations for the target task are available. We also evaluate cross-encoders trained in a weakly supervised manner based on machine-translated datasets from a high resource domain. Our system is publicly available as an extensible Python toolkit. Results: xMEN improves the state-of-the-art performance across a wide range of multilingual benchmark datasets. Weakly supervised cross-encoders are effective when no training data is available for the target task. Through the compatibility of xMEN with the BigBIO framework, it can be easily used with existing and prospective datasets. Discussion: Our experiments show the importance of balancing the output of general-purpose candidate generators with subsequent trainable re-rankers, which we achieve through a rank regularization term in the loss function of the cross-encoder. However, error analysis reveals that multi-word expressions and other complex entities are still challenging. Conclusion: xMEN exhibits strong performance for medical entity normalization in multiple languages, even when no labeled data and few terminology aliases for the target language are available. Its configuration system and evaluation modules enable reproducible benchmarks. Models and code are available online at the following URL: https://github.com/hpi-dhc/xmen