b'Barbara Plank'

research

∙ 09/04/2023

Donkii: Can Annotation Error Detection Methods Find Errors in Instruction-Tuning Datasets?

Instruction-tuning has become an integral part of training pipelines for...

0 Leon Weber-Genzel, et al. ∙

research

∙ 07/28/2023

Uncertainty in Natural Language Generation: From Theory to Applications

Recent advances of powerful Language Models have allowed Natural Languag...

0 Joris Baan, et al. ∙

research

∙ 05/31/2023

Findings of the VarDial Evaluation Campaign 2023

This report presents the results of the shared tasks organized as part o...

0 Noëmi Aepli, et al. ∙

research

∙ 05/31/2023

ActiveAED: A Human in the Loop Improves Annotation Error Detection

Manually annotated datasets are crucial for training and evaluating Natu...

0 Leon Weber, et al. ∙

research

∙ 05/24/2023

How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives

Recently, various intermediate layer distillation (ILD) objectives have ...

0 Xinpeng Wang, et al. ∙

research

∙ 05/20/2023

ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain

The increasing number of benchmarks for Natural Language Processing (NLP...

0 Mike Zhang, et al. ∙

research

∙ 05/19/2023

What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability

In Natural Language Generation (NLG) tasks, for any input, multiple comm...

0 Mario Giulianelli, et al. ∙

research

∙ 05/18/2023

Silver Syntax Pre-training for Cross-Domain Relation Extraction

Relation Extraction (RE) remains a challenging task, especially when con...

0 Elisa Bassignana, et al. ∙

research

∙ 05/18/2023

Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction

Most research in Relation Extraction (RE) involves the English language,...

0 Elisa Bassignana, et al. ∙

research

∙ 05/09/2023

Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data

Transferring information retrieval (IR) models from a high-resource lang...

0 Robert Litschko, et al. ∙

research

∙ 04/28/2023

SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)

NLP datasets annotated with human judgments are rife with disagreements ...

0 Elisa Leonardelli, et al. ∙

research

∙ 04/20/2023

Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages

One of the challenges with finetuning pretrained language models (PLMs) ...

0 Verena Blaschke, et al. ∙

research

∙ 04/19/2023

Low-resource Bilingual Dialect Lexicon Induction with Large Language Models

Bilingual word lexicons are crucial tools for multilingual natural langu...

0 Ekaterina Artemova, et al. ∙

research

∙ 04/19/2023

A Survey of Corpora for Germanic Low-Resource Languages and Dialects

Despite much progress in recent years, the vast majority of work in natu...

0 Verena Blaschke, et al. ∙

research

∙ 11/04/2022

The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation

Human variation in labeling is often considered noise. Annotation projec...

0 Barbara Plank, et al. ∙

research

∙ 10/28/2022

Stop Measuring Calibration When Humans Disagree

Calibration is a popular framework to evaluate whether a classifier know...

0 Joris Baan, et al. ∙

research

∙ 10/21/2022

Spectral Probing

Linguistic information is encoded at varying timescales (subwords, phras...

0 Max Müller-Eberstein, et al. ∙

research

∙ 10/20/2022

Evidence > Intuition: Transferability Estimation for Encoder Selection

With the increase in availability of large pre-trained language models (...

1 Elisa Bassignana, et al. ∙

research

∙ 10/17/2022

CrossRE: A Cross-Domain Dataset for Relation Extraction

Relation Extraction (RE) has attracted increasing attention, but current...

0 Elisa Bassignana, et al. ∙

research

∙ 09/23/2022

An Interdisciplinary Perspective on Evaluation and Experimental Design for Visual Text Analytics: Position Paper

Appropriate evaluation and experimental design are fundamental for empir...

6 Kostiantyn Kucher, et al. ∙

research

∙ 09/16/2022

Skill Extraction from Job Postings using Weak Supervision

Aggregated data obtained from job postings provide powerful insights int...

6 Mike Zhang, et al. ∙

research

∙ 06/10/2022

Sort by Structure: Language Model Ranking as Dependency Probing

Making an informed choice of pre-trained language model (LM) is critical...

0 Max Müller-Eberstein, et al. ∙

research

∙ 05/03/2022

Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning

Skill Classification (SC) is the task of classifying job competences fro...

13 Mike Zhang, et al. ∙

research

∙ 04/28/2022

What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification

Over the last five years, research on Relation Extraction (RE) witnessed...

0 Elisa Bassignana, et al. ∙

research

∙ 04/27/2022

SkillSpan: Hard and Soft Skill Extraction from English Job Postings

Skill Extraction (SE) is an important and widely-studied task useful to ...

8 Mike Zhang, et al. ∙

research

∙ 04/13/2022

Experimental Standards for Deep Learning Research: A Natural Language Processing Perspective

The field of Deep Learning (DL) has undergone explosive growth during th...

50 Dennis Ulmer, et al. ∙

research

∙ 03/24/2022

Probing for Labeled Dependency Trees

Probing has become an important tool for analyzing representations in Na...

0 Max Müller-Eberstein, et al. ∙

research

∙ 12/09/2021

How Universal is Genre in Universal Dependencies?

This work provides the first in-depth analysis of genre in Universal Dep...

0 Max Müller-Eberstein, et al. ∙

research

∙ 09/10/2021

Genre as Weak Supervision for Cross-lingual Dependency Parsing

Recent work has shown that monolingual masked language models learn to r...

0 Max Müller-Eberstein, et al. ∙

research

∙ 09/09/2021

Cartography Active Learning

We propose Cartography Active Learning (CAL), a novel Active Learning (A...

35 Mike Zhang, et al. ∙

research

∙ 07/08/2021

Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)

Welcome to WeaSuL 2021, the First Workshop on Weakly Supervised Learning...

0 Michael A. Hedderich, et al. ∙

research

∙ 05/24/2021

DaN+: Danish Nested Named Entities and Lexical Normalization

This paper introduces DaN+, a new multi-domain corpus and annotation gui...

12 Barbara Plank, et al. ∙

research

∙ 05/24/2021

De-identification of Privacy-related Entities in Job Postings

De-identification is the task of detecting privacy-related entities in t...

14 Kristian Nørgaard Jensen, et al. ∙

research

∙ 05/15/2021

From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding

The lack of publicly available evaluation data for low-resource language...

0 Rob van der Goot, et al. ∙

research

∙ 03/01/2021

On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions

Recent complementary strands of research have shown that leveraging info...

0 Rob van der Goot, et al. ∙

research

∙ 12/10/2020

Longitudinal Citation Prediction using Temporal Graph Neural Networks

Citation count prediction is the task of predicting the number of citati...

0 Andreas Nugaard Holm, et al. ∙

research

∙ 05/31/2020

Neural Unsupervised Domain Adaptation in NLP—A Survey

Deep neural networks excel at learning from labeled data and achieve sta...

0 Alan Ramponi, et al. ∙

research

∙ 05/29/2020

Massive Choice, Ample Tasks (MaChAmp):A Toolkit for Multi-task Learning in NLP

Transfer learning, particularly approaches that combine multi-task learn...

0 Rob van der Goot, et al. ∙

research

∙ 05/25/2020

FT Speech: Danish Parliament Speech Corpus

This paper introduces FT Speech, a new speech corpus created from the re...

0 Andreas Kirkedal, et al. ∙

research

∙ 03/05/2020

Neural Cross-Lingual Transfer and Limited Annotated Data for Named Entity Recognition in Danish

Named Entity Recognition (NER) has greatly advanced by the introduction ...

0 Barbara Plank, et al. ∙

research

∙ 06/10/2019

Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering

We study the issue of catastrophic forgetting in the context of neural m...

0 Claudio Greco, et al. ∙

research

∙ 11/21/2018

The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging

In natural language processing, the deep learning revolution has shifted...

0 Barbara Plank, et al. ∙

research

∙ 08/29/2018

Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging

We introduce DsDs: a cross-lingual neural part-of-speech tagger that lea...

0 Barbara Plank, et al. ∙

research

∙ 05/08/2018

Bleaching Text: Abstract Features for Cross-lingual Gender Prediction

Gender prediction has typically focused on lexical and social network fe...

0 Rob van der Goot, et al. ∙

research

∙ 04/25/2018

Strong Baselines for Neural Semi-supervised Learning under Domain Shift

Novel neural models have been proposed in recent years for learning unde...

0 Sebastian Ruder, et al. ∙

research

∙ 10/26/2017

ALL-IN-1: Short Text Classification with One Model for All Languages

We present ALL-IN-1, a simple model for multilingual text classification...

0 Barbara Plank, et al. ∙

research

∙ 07/17/2017

Learning to select data for transfer learning with Bayesian Optimization

Domain similarity measures can be used to gauge adaptability and select ...

0 Sebastian Ruder, et al. ∙

research

∙ 07/17/2017

To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging

Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, ...

0 Rob van der Goot, et al. ∙

research

∙ 01/11/2017

Parsing Universal Dependencies without training

We propose UDP, the first training-free parser for Universal Dependencie...

0 Héctor Martínez Alonso, et al. ∙

research

∙ 12/07/2016

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Multitask learning has been applied successfully to a range of tasks, mo...

0 Héctor Martínez Alonso, et al. ∙

Barbara Plank

Featured Co-authors