Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text

Lukas Lange, Anastasiia Iurshina, Heike Adel, Jannik Strötgen


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.
Anthology ID:
2020.repl4nlp-1.14
Volume:
Proceedings of the 5th Workshop on Representation Learning for NLP
Month:
July
Year:
2020
Address:
Online
Editors:
Spandana Gella, Johannes Welbl, Marek Rei, Fabio Petroni, Patrick Lewis, Emma Strubell, Minjoon Seo, Hannaneh Hajishirzi
Venue:
RepL4NLP
SIG:
SIGREP
Publisher:
Association for Computational Linguistics
Note:
Pages:
103–109
Language:
URL:
https://aclanthology.org/2020.repl4nlp-1.14
DOI:
10.18653/v1/2020.repl4nlp-1.14
Bibkey:
Cite (ACL):
Lukas Lange, Anastasiia Iurshina, Heike Adel, and Jannik Strötgen. 2020. Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text. In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 103–109, Online. Association for Computational Linguistics.
Cite (Informal):
Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text (Lange et al., RepL4NLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.repl4nlp-1.14.pdf
Video:
 http://slideslive.com/38929780
Data
Basque TimeBankCatalan TimeBank 1.0French TimebankKRAUTSSpanish TimeBank 1.0TempEval-3TimeBankPT