Heather Lent

Common Sense Bias in Semantic Role Labeling

2021

Large-scale language models such as ELMo and BERT have pushed the horizon of what is possible in semantic role labeling (SRL), solving the out-of-vocabulary problem and enabling end-to-end systems, but they have also introduced significant …

Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter?

2023

Monolinguals make up a minority of the world’s speakers, and yet most language technologies lag behind in handling linguistic behaviours produced by bilingual and multilingual speakers. A commonly observed phenomenon in such communities is code-mixing, …

Text Embedding Inversion Security for Multilingual Language Models

2024

Textual data is often represented as realnumbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS).However, storing sensitive information as embeddings can be susceptible to security …