Noura Al Moubayed

On the Hierarchical Information in a Single Contextualised Word Representation (Student Abstract)

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Contextual word embeddings produced by neural language models, such as BERT or ELMo, have seen widespread application and performance gains across many Natural Language Processing tasks, suggesting rich linguistic features encoded in their representations. This …

RAR-b: Reasoning as Retrieval Benchmark

2024 · arXiv (Cornell University)

Semantic textual similartiy (STS) and information retrieval tasks (IR) tasks have been the two major avenues to record the progress of embedding models in the past few years. Under the emerging Retrieval-augmented Generation (RAG) paradigm, …