AAU NLP
AAU NLP
People
Publications
Events
Light
Dark
Automatic
Natural Language Processing
What is “Typological Diversity” in NLP?
The NLP research community has devoted increased attention to languages beyond English, resulting in considerable improvements for …
Esther Ploeger
,
Wessel Poelman
,
Miryam De Lhoneux
,
Johannes Bjerva
PDF
Cite
Code
Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks
Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, …
Yiyi Chen
,
Russa Biswas
,
Heather Lent
,
Johannes Bjerva
PDF
Cite
Text Embedding Inversion Security for Multilingual Language Models
Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) …
Yiyi Chen
,
Heather Lent
,
Johannes Bjerva
PDF
Cite
Code
A Principled Framework for Evaluating on Typologically Diverse Languages
Beyond individual languages, multilingual natural language processing (NLP) research increasingly aims to develop models that perform …
Esther Ploeger
,
Wessel Poelman
,
Andreas Holck Høeg-Petersen
,
Anders Schlichtkrull
,
Miryam De Lhoneux
,
Johannes Bjerva
PDF
Cite
Code
Multilingual Gradient Word-Order Typology from Universal Dependencies
While information from the field of linguistic typology has the potential to improve performance on NLP tasks, reliable typological …
Emi Baylor
,
Esther Ploeger
,
Johannes Bjerva
PDF
Cite
A Call for Consistency in Reporting Typological Diversity
In order to draw generalizable conclusions about the performance of multilingual models across languages, it is important to evaluate …
Wessel Poelman
,
Esther Ploeger
,
Miryam De Lhoneux
,
Johannes Bjerva
PDF
Cite
The Past, Present, and Future of Typological Databases in NLP
Typological information has the potential to be beneficial in the development of NLP models, particularly for low-resource languages. …
Emi Baylor
,
Esther Ploeger
,
Johannes Bjerva
PDF
Cite
The Role of Typological Feature Prediction in NLP and Linguistics
Computational typology has gained traction in the field of Natural Language Processing (NLP) in recent years, as evidenced by the …
Johannes Bjerva
PDF
Cite
Cite
×