Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text

2020/05/19 by Lukas Lange, Lange, Lukas, Anastasiia Iurshina +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.2005.09392

RepL4NLP at ACL 2020

arxiv created 2020/05/19 · arxiv updated 2020/05/20

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.

Related

• Multilingual Normalization of Temporal Expressions with Masked Language Models
• BERT got a Date: Introducing Transformers to Temporal Tagging
• Adversarial Neural Networks for Cross-lingual Sequence Tagging
• XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction
• A Novel Methodology for Enhancing Cross-language and Domain Adaptability in Temporal Expression Normalization