Lea Frermann

Optimising Equal Opportunity Fairness in Model Training

A Shen, X Han, T Cohn, T Baldwin, L Frermann

Conference Proceedings  |  2022  |  NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leadin..

A Computational Acquisition Model for Multimodal Word Categorization

U Berger, G Stanovsky, O Abend, L Frermann

Conference Proceedings  |  2022  |  NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Recent advances in self-supervised modeling of text and images open new opportunities for computational models of child language a..

FairLib: A Unified Framework for Assessing and Improving Fairness

X Han, A Shen, Y Li, L Frermann, T Baldwin, T Cohn

Conference Proceedings  |  2022  |  EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session

Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data

K Kurniawan, L Frermann, P Schulz, T Cohn

Conference Proceedings  |  2022  |  NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming..

Word formation supports efficient communication: The case of compounds

A Xu, C Kemp, L Frermann, Y Xu

Conference Proceedings  |  2022  |  Proceedings of the 44th Annual Meeting of the Cognitive Science Society: Cognitive Diversity, CogSci 2022

Principled Analysis of Energy Discourse across Domains with Thesaurus-based Automatic Topic Labeling

T Scelsi, AM Arranz, L Frermann

Conference Proceedings  |  2021  |  ALTA 2021 - Proceedings of the 19th Workshop of the Australasian Language Technology Association

PPT: Parsimonious parser transfer for unsupervised cross-lingual adaptation

K Kurniawan, L Frermann, P Schulz, T Cohn

Conference Proceedings  |  2021  |  EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple 'd..

Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames

S Khanehzar, T Cohn, G Mikolajczak, A Turpin, L Frermann

Conference Proceedings  |  2021  |  NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Understanding how news media frame political issues is important due to its impact on public attitudes, yet hard to automate. Comp..

Multi-modal Intent Classification for Assistive Robots with Large-scale Naturalistic Datasets

K Mathew, VS Aditya Tarigoppula, L Frermann

Conference Proceedings  |  2021  |  ALTA 2021 - Proceedings of the 19th Workshop of the Australasian Language Technology Association

Categorization in the Wild: Category and Feature Learning across Languages

L Frermann, M Lapata

Conference Proceedings  |  2021  |  Proceedings of the 43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021