28 citations · 129 across the 32 of their papers we have counts for
5 papers · 1 filter
When Do Decompositions Help for Machine Reading?
Kangda Wei, Dawn Lawrie, Benjamin Van Durme +2
Answering complex questions often requires multi-step reasoning in order to obtain the final answer. Most research into decompositions of complex questions involves open-domain sys…
Defending Against Disinformation Attacks in Open-Domain Question Answering
Orion Weller, Aleem Khan, Nathaniel Weir +2
Recent work in open-domain question answering (ODQA) has shown that adversarial poisoning of the search collection can cause large drops in accuracy for production systems. However…
Pretrained Models for Multilingual Federated Learning
Orion Weller, Marc Marone, Vladimir Braverman +2
Since the advent of Federated Learning (FL), research has applied these methods to natural language processing (NLP) tasks. Despite a plethora of papers in FL for NLP, no previous…
When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning
Orion Weller, Kevin Seppi, Matt Gardner
Transfer learning (TL) in natural language processing (NLP) has seen a surge of interest in recent years, as pre-trained models have shown an impressive ability to transfer to nove…
End-to-End Speech Translation for Code Switched Speech
Orion Weller, Matthias Sperber, Telmo Pires +4
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the oft…