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

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

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

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
Original languageEnglish
Pages (from-to)410-428
Number of pages19
JournalTransactions of the Association for Computational Linguistics
Publication statusPublished - 26 Apr 2021


Dive into the research topics of 'Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages'. Together they form a unique fingerprint.

Cite this