Isabelle Augenstein

Prof. Isabelle Augenstein

University of Copenhagen, Copenhagen, Hovedstaden, Denmark
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
IAIsabelle Augenstein
Isabelle Augenstein
TBTimothy Baldwin
Timothy Baldwin
MCMeeyoung Cha
Meeyoung Cha
TCTanmoy Chakraborty
Tanmoy Chakraborty
GCGiovanni Luca Ciampaglia
Giovanni Luca Ciampaglia
GZGiovanni Zagni
Giovanni Zagni

17 July 2019 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Closed access
PDF file
SRSebastian Ruder
Sebastian Ruder
JBJoachim Bingel
Joachim Bingel
IAIsabelle Augenstein
Isabelle Augenstein
ASAnders Søgaard
Anders Søgaard
Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c) the appropriate relative weights of the different task losses. Recent work has addressed each of the above problems in isolation. In this work we present an approach that learns a latent multi-task architecture that jointly addresses (a)–(c). We present experiments on synthetic data and data from OntoNotes 5.0, including four different tasks and seven different domains. Our extension consistently outperforms previous approaches to learning latent architectures for multi-task problems and achieves up to 15% average error reductions over common approaches to MTL.

2 February 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
ARAnna Rogers
Anna Rogers
MGMatt Gardner
Matt Gardner
IAIsabelle Augenstein
Isabelle Augenstein
Alongside huge volumes of research on deep learning models in NLP in the recent years, there has been much work on benchmark datasets needed to track modeling progress. Question answering and reading comprehension have been particularly prolific in this regard, with more than 80 new datasets appearing in the past 2 years. This study is the largest survey of the field to date. We provide an overview of the various formats and domains of the current resources, highlighting the current lacunae for future work. We further discuss the current classifications of “skills” that question answering/reading comprehension systems are supposed to acquire and propose a new taxonomy. The supplementary materials survey the current multilingual resources and monolingual resources for languages other than English, and we discuss the implications of overfocusing on English. The study is aimed at both practitioners looking for pointers to the wealth of existing data and at researchers working on new resources.

1 January 2019
Verified
Conference Paper
Open access
PDF file
IAIsabelle Augenstein
Isabelle Augenstein
CLChristina Lioma
Christina Lioma
DWDongsheng Wang
Dongsheng Wang
LLLucas Chaves Lima
Lucas Chaves Lima
CHCasper Hansen
Casper Hansen
JSJakob Grue Simonsen
Jakob Grue Simonsen
Isabelle Augenstein, Christina Lioma, Dongsheng Wang, Lucas Chaves Lima, Casper Hansen, Christian Hansen, Jakob Grue Simonsen. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

1 January 2023
Verified
Conference Paper
Open access
PDF file
AAArnav Arora
Arnav Arora
LKLucie-Aimée Kaffee
Lucie-Aimée Kaffee
IAIsabelle Augenstein
Isabelle Augenstein
Arnav Arora, Lucie-aimée Kaffee, Isabelle Augenstein. Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). 2023.

1 March 2018 in Information Processing & Management
Verified
Journal Article
Open access
Arkaitz ZubiagaArkaitz Zubiaga
Arkaitz Zubiaga
EKElena Kochkina
Elena Kochkina
MLMaria Liakata
Maria Liakata
RPRob Procter
Rob Procter
MLMichal Lukasik
Michal Lukasik
IAIsabelle Augenstein
Isabelle Augenstein
Rumour stance classification, defined as classifying the stance of specific social media posts into one of supporting, denying, querying or commenting on an earlier post, is becoming of increasing interest to researchers. While most previous work has focused on using individual tweets as classifier inputs, here we report on the performance of sequential classifiers that exploit the discourse features inherent in social media interactions or 'conversational threads'. Testing the effectiveness of four sequential classifiers -- Hawkes Processes, Linear-Chain Conditional Random Fields (Linear CRF), Tree-Structured Conditional Random Fields (Tree CRF) and Long Short Term Memory networks (LSTM) -- on eight datasets associated with breaking news stories, and looking at different types of local and contextual features, our work sheds new light on the development of accurate stance classifiers. We show that sequential classifiers that exploit the use of discourse properties in social media conversations while using only local features, outperform non-sequential classifiers. Furthermore, we show that LSTM using a reduced set of features can outperform the other sequential classifiers; this performance is consistent across datasets and across types of stances. To conclude, our work also analyses the different features under study, identifying those that best help characterise and distinguish between stances, such as supporting tweets being more likely to be accompanied by evidence than denying tweets. We also set forth a number of directions for future research