Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages

Edoardo M. Ponti, Ivan Vulić, Ryan Cotterell, Marinela Parovic, Roi Reichart, Anna Korhonen


Abstract
Most combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task–language combinations with available data to low-resource ones? In this work, we propose a Bayesian generative model for the space of neural parameters. We assume that this space can be factorized into latent variables for each language and each task. We infer the posteriors over such latent variables based on data from seen task–language combinations through variational inference. This enables zero-shot classification on unseen combinations at prediction time. For instance, given training data for named entity recognition (NER) in Vietnamese and for part-of-speech (POS) tagging in Wolof, our model can perform accurate predictions for NER in Wolof. In particular, we experiment with a typologically diverse sample of 33 languages from 4 continents and 11 families, and show that our model yields comparable or better results than state-of-the-art, zero-shot cross-lingual transfer methods. Our code is available at github.com/cambridgeltl/parameter-factorization.
Anthology ID:
2021.tacl-1.25
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
410–428
Language:
URL:
https://aclanthology.org/2021.tacl-1.25
DOI:
10.1162/tacl_a_00374
Bibkey:
Cite (ACL):
Edoardo M. Ponti, Ivan Vulić, Ryan Cotterell, Marinela Parovic, Roi Reichart, and Anna Korhonen. 2021. Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages. Transactions of the Association for Computational Linguistics, 9:410–428.
Cite (Informal):
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages (Ponti et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.25.pdf
Video:
 https://aclanthology.org/2021.tacl-1.25.mp4