Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text

TL;DR

This paper introduces a multilingual neural approach for extracting temporal expressions from text, utilizing adversarial training to align embeddings across languages, achieving state-of-the-art cross-lingual transfer performance.

Contribution

It presents a novel adversarial training method for aligning multilingual embedding spaces, enabling effective temporal expression extraction across multiple languages.

Findings

Achieved new state-of-the-art results in cross-lingual transfer tasks.

Developed a single multilingual model transferable to unseen languages.

Demonstrated the effectiveness of adversarial alignment in multilingual temporal tagging.

Abstract

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.