Multilingual Learning

Multi-lingual learning is concerned with training models to work well for multiple languages, including low-resource ones. We research methods for enabling information sharing between multiple languages, and also study how to utilise typological knowledge bases to this end. We are currently involved in three larger funded projects on this.

Multi3Generation is a COST Action that funds collaboration of researchers in Europe and abroad. The project is coordinated by Isabelle Augenstein, and its goals are to study language generation using multi-task, multilingual and multi-modal signals.

We are further partner in a research project funded by the Swedish Research Council coordinated by Robert Östling. Its goals are to study structured multilinguality, i.e. the idea of using language representations and typological knowledge bases to guide which information to share between specific languages.

Lastly, Andrea Lekkas’ industrial PhD project with Ordbogen, supported by Innovation Fund Denmark, focuses on multilingual language modelling for developing writing assistants.

lld multilingual-learning

Publications

While the prevalence of large pre-trained language models has led to significant improvements in the performance of NLP systems, recent …
PDF Project Project

Pre-trained language models have been known to perpetuate biases from the underlying datasets to downstream tasks. However, these …
PDF Project Project

Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially …
PDF Project Project

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic …
PDF Project Project

The success of multilingual pre-trained models is underpinned by their ability to learn representations shared by multiple languages …
PDF Project Project

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle …
PDF Project

This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generation (CA18231), an …
PDF Project Project

The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts …
PDF Project Project Project

Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. …
PDF Code Project Project

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features …
PDF Project Project

Learning what to share between tasks has been a topic of high importance recently, as strategic sharing of knowledge has been shown to …
PDF Code Project Project Project Project

Typological knowledge bases (KBs) such as WALS contain information about linguistic properties of the world’s languages. They …
PDF Code Dataset Project Project

We propose a novel Chinese character conversion model that can disambiguate between mappings and convert between the two scripts. The …
PDF Dataset Project Video

Although the vast majority of knowledge bases KBs are heavily biased towards English, Wikipedias do cover very different topics in …
PDF Project Project Project Project

The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages …
PDF Project Project

In the Principles and Parameters framework, the structural features of languages depend on parameters that may be toggled on or off, …
PDF Project Project Slides Video

A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words …
PDF Project

Previous work has suggested that parameter sharing between transition-based neural dependency parsers for related languages can lead to …
PDF Project Project Poster

This paper documents the Team Copenhagen system which placed first in the CoNLL–SIGMORPHON 2018 shared task on universal …
PDF Project Project

A core part of linguistic typology is the classification of languages according to linguistic properties, such as those detailed in the …
PDF Code Project

Although linguistic typology has a long history, computational approaches have only recently gained popularity. The use of distributed …
PDF Project Slides