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 …
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, …
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) …
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 …
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 …
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 …
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. …
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 …
PDF Cite