Multilingual Normalization of Temporal Expressions with Masked Language Models
This addresses the costly rule creation issue for multilingual temporal normalization, benefiting NLP applications, though it is incremental as it builds on existing neural approaches.
The paper tackled the problem of temporal expression normalization in multilingual settings by proposing a neural method based on masked language modeling, which outperformed rule-based systems with up to 33 F1 improvement on average for low-resource languages.
The detection and normalization of temporal expressions is an important task and preprocessing step for many applications. However, prior work on normalization is rule-based, which severely limits the applicability in real-world multilingual settings, due to the costly creation of new rules. We propose a novel neural method for normalizing temporal expressions based on masked language modeling. Our multilingual method outperforms prior rule-based systems in many languages, and in particular, for low-resource languages with performance improvements of up to 33 F1 on average compared to the state of the art.