3 citations · 5 across the 4 of their papers we have counts for
7 papers · 1 filter
A survey on improving NLP models with human explanations
Mareike Hartmann, Daniel Sonntag
Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity w…
MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model
Rasmus Kær Jørgensen, Mareike Hartmann, Xiang Dai +1
Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the…
Mapping (Dis-)Information Flow about the MH17 Plane Crash
Mareike Hartmann, Yevgeniy Golovchenko, Isabelle Augenstein
Digital media enables not only fast sharing of information, but also disinformation. One prominent case of an event leading to circulation of disinformation on social media is the…
Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction
Yova Kementchedjhieva, Mareike Hartmann, Anders Søgaard
The task of bilingual dictionary induction (BDI) is commonly used for intrinsic evaluation of cross-lingual word embeddings. The largest dataset for BDI was generated automatically…
Issue Framing in Online Discussion Fora
Mareike Hartmann, Tallulah Jansen, Isabelle Augenstein +1
In online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic. In social science, this is refer…
Why is unsupervised alignment of English embeddings from different algorithms so hard?
Mareike Hartmann, Yova Kementchedjhieva, Anders Søgaard
This paper presents a challenge to the community: Generative adversarial networks (GANs) can perfectly align independent English word embeddings induced using the same algorithm, b…