12 citations · 20 across the 14 of their papers we have counts for
16 papers
Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right
Heather Lent
Despite mounting evidence that multilinguality can be easily weaponized against language models (LMs), works across NLP Security remain overwhelmingly English-centric. In terms of…
Limited-Resource Adapters Are Regularizers, Not Linguists
Marcell Fekete, Nathaniel R. Robinson, Ernests Lavrinovics +4
Cross-lingual transfer from related high-resource languages is a well-established strategy to enhance low-resource language technologies. Prior work has shown that adapters show pr…
NLP Security and Ethics, in the Wild
Heather Lent, Erick Galinkin, Yiyi Chen +3
As NLP models are used by a growing number of end-users, an area of increasing importance is NLP Security (NLPSec): assessing the vulnerability of models to malicious attacks and d…
How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP
Kushal Tatariya, Artur Kulmizev, Wessel Poelman +6
Wikipedia's perceived high quality and broad language coverage have established it as a fundamental resource in NLP. However, in recent years, such assumptions of high quality have…
Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
Aditya Joshi, Diptesh Kanojia, Heather Lent +2
Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such…
Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks
Yiyi Chen, Russa Biswas, Heather Lent +1
Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, backdoor, and embedding inversion attacks. In respons…
Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification
Kushal Tatariya, Heather Lent, Johannes Bjerva +1
Emotion classification is a challenging task in NLP due to the inherent idiosyncratic and subjective nature of linguistic expression, especially with code-mixed data. Pre-trained l…
Text Embedding Inversion Security for Multilingual Language Models
Yiyi Chen, Heather Lent, Johannes Bjerva
Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However,…
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Heather Lent, Kushal Tatariya, Raj Dabre +18
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of h…
Ancestor-to-Creole Transfer is Not a Walk in the Park
Heather Lent, Emanuele Bugliarello, Anders Søgaard
We aim to learn language models for Creole languages for which large volumes of data are not readily available, and therefore explore the potential transfer from ancestor languages…
What a Creole Wants, What a Creole Needs
Heather Lent, Kelechi Ogueji, Miryam de Lhoneux +2
In recent years, the natural language processing (NLP) community has given increased attention to the disparity of efforts directed towards high-resource languages over low-resourc…
Challenges and Strategies in Cross-Cultural NLP
Daniel Hershcovich, Stella Frank, Heather Lent +11
Various efforts in the Natural Language Processing (NLP) community have been made to accommodate linguistic diversity and serve speakers of many different languages. However, it is…
On Language Models for Creoles
Heather Lent, Emanuele Bugliarello, Miryam de Lhoneux +2
Creole languages such as Nigerian Pidgin English and Haitian Creole are under-resourced and largely ignored in the NLP literature. Creoles typically result from the fusion of a for…
Compositional Generalization in Multilingual Semantic Parsing over Wikidata
Ruixiang Cui, Rahul Aralikatte, Heather Lent +1
Semantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on English resources, s…
Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards
Rahul Aralikatte, Mostafa Abdou, Heather Lent +2
Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer to the same entity, an…
Rewarding Coreference Resolvers for Being Consistent with World Knowledge
Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez +5
Unresolved coreference is a bottleneck for relation extraction, and high-quality coreference resolvers may produce an output that makes it a lot easier to extract knowledge triples…