Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text
This addresses the need for multilingual temporal tagging, which is incremental as it extends neural methods from monolingual to multilingual contexts.
The paper tackles the problem of extracting temporal expressions from text in multilingual settings by using adversarial training to align embedding spaces, resulting in a single model that achieves state-of-the-art performance in cross-lingual transfer experiments.
Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers. However, all of them focus on monolingual settings. In this paper, we explore multilingual methods for the extraction of temporal expressions from text and investigate adversarial training for aligning embedding spaces to one common space. With this, we create a single multilingual model that can also be transferred to unseen languages and set the new state of the art in those cross-lingual transfer experiments.