Learning with Limited Labelled Data

Learning with limited labelled data is useful for small domains or languages with little resources. Methods we research to mitigate problems arising in these contexts include multi-task learning, weakly supervised and zero-shot learning.

This is a cross-cutting theme in most of our research. Two funded projects specifically addressing this are Multi3Generation and Andreas Nugaard Holm’s industrial PhD project with BASE Life Science, supported by Innovation Fund Denmark.

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.

Andreas Nugaard Holm’s industrial PhD project focuses on transfer learning and domain adaptation for scientific text.

lld limited-data

Publications

Explainable AI methods facilitate the understanding of model behaviour, yet, small, imperceptible perturbations to inputs can vastly …
PDF Project Project

The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the …
PDF Project Project

The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional …
PDF Project

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One …
Preprint PDF Project

Data-driven analyses of biases in historical texts can help illuminate the origin and development of biases prevailing in modern …
PDF Project

NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses …
PDF Project

The task of Stance Detection is concerned with identifying the attitudes expressed by an author towards a target of interest. This task …
PDF Project Project

Selecting an effective training signal for tasks in natural language processing is difficult: expert annotations are expensive, and …
PDF Project

Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when …
PDF Project Project Project

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to …
PDF Project

Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of …
PDF Project Project Project

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

We propose a novel framework for cross-lingual content flagging with limited target-language data, which significantly outperforms …
PDF Project

Explanations shed light on a machine learning model’s rationales and can aid in identifying deficiencies in its reasoning …
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

For natural language processing (NLP) tasks such as sentiment or topic classification, currently prevailing approaches heavily rely on …
PDF Project

Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time. Prior work …
PDF Project Project

Stance detection concerns the classification of a writer’s viewpoint towards a target. There are different task variants, e.g., …
PDF Project Project

As NLP models are increasingly deployed in socially situated settings such as online abusive content detection, ensuring these models …
PDF Project Project Project

Public trust in science depends on honest and factual communication of scientific papers. However, recent studies have demonstrated a …
PDF Project Project Project

Emotion lexica are commonly used resources to combat data poverty in automatic emotion detection. However, methodological issues emerge …
PDF 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

Scientific document understanding is challenging as the data is highly domain specific and diverse. However, datasets for tasks with …
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

In this paper, we describe our participation in the TREC Health Misinformation Track 2020. We submitted 11 runs to the Total Recall …
PDF Project Project

Subjectivity is the expression of internal opinions or beliefs which cannot be objectively observed or verified, and has been shown to …
PDF Dataset Project Project

In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than …
PDF Code 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

A critical component of automatically combating misinformation is the detection of fact check-worthiness, i.e. determining if a piece …
PDF Code 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

While state-of-the-art NLP explainability (XAI) methods focus on supervised, per-instance end or diagnostic probing task evaluation[4, …
PDF Code Project Project

In this paper, we extend the task of semantic textual similarity to include sentences which contain emojis. Emojis are ubiquitous on …
PDF Project

Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens …
PDF Code Project Project

Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent …
PDF Project Project

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

Multi-task learning and self-training are two common ways to improve a machine learning model’s performance in settings with …
PDF Project

Studying to what degree the language we use is gender-specific has long been an area of interest in socio-linguistics. Studies have …
PDF Code Project Project Slides

When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning …
PDF Code Project Slides Video

In online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects …
PDF Project Project

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In …
PDF Code Project Slides

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

Neural part-of-speech (POS) taggers are known to not perform well with little training data. As a step towards overcoming this problem, …
PDF Project

We combine multi-task learning and semisupervised learning by inducing a joint embedding space between disparate label spaces and …
PDF Code Project Project Slides Video

We take a multi-task learning approach to the shared Task 1 at SemEval-2018. The general idea concerning the model structure is to use …
PDF Project

Keyphrase boundary classification (KBC) is the task of detecting keyphrases in scientific articles and labelling them with respect to …
PDF Project Project Project Poster