5 papers
Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork
Vasudevan Nedumpozhimana, John Kelleher
Sentence representation learning is still an open challenge in Natural Language Processing. In this work, we propose a new self-supervised framework for learning sentence represent…
Analysing the Linearity of Linguistic Relations in Language Model Embedding Spaces
Vasudevan Nedumpozhimana, Fathima Thekkekara, John Kelleher
We propose a framework to analyse how strongly different linguistic relations are linearly encoded in language model embedding spaces. We formalise linear encoding via a constraine…
The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions
Filip Klubicka, Vasudevan Nedumpozhimana, Sneha Rautmare +3
In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2…
Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11
Serving open-weight language models on premises forces a trade-off between accuracy and computational cost. Hosting models of different sizes lets easy queries go to a small, effic…
Topic Aware Probing: From Sentence Length Prediction to Idiom Identification how reliant are Neural Language Models on Topic?
Vasudevan Nedumpozhimana, John D. Kelleher
Transformer-based Neural Language Models achieve state-of-the-art performance on various natural language processing tasks. However, an open question is the extent to which these m…