no code implementations • ECNLP (ACL) 2022 • Kristen Howell, Jian Wang, Akshay Hazare, Joseph Bradley, Chris Brew, Xi Chen, Matthew Dunn, Beth Hockey, Andrew Maurer, Dominic Widdows
We demonstrate that knowledge distillation can be used not only to reduce model size, but to simultaneously adapt a contextual language model to a specific domain.
no code implementations • 28 Mar 2024 • Dominic Widdows, Willie Aboumrad, Dohun Kim, Sayonee Ray, Jonathan Mei
In this context, we argue that "hallucinations" in modern artificial intelligence systems are a misunderstanding of the way facts are conceptualized: language can express many plausible hypotheses, of which only a few become actual.
no code implementations • 16 Jan 2024 • Emily Gao, Dominic Widdows
As a tech company, Grab has expanded from transportation to food delivery, aiming to serve Southeast Asia with hyperlocalized applications.
no code implementations • 6 Feb 2023 • Dominic Widdows, Jyoti Rani, Emmanuel Pothos
The claim is not that the human brain uses qubits and quantum circuits explicitly (just like the use of Boolean set theory does not require the brain to be using classical bits), but that the mathematics shared between quantum cognition and quantum computing motivates the exploration of quantum computers for cognition modeling.
no code implementations • 5 Jun 2022 • Dominic Widdows, Aaranya Alexander, Daiwei Zhu, Chase Zimmerman, Arunava Majumder
This paper describes experiments showing that some tasks in natural language processing (NLP) can already be performed using quantum computers, though so far only with small datasets.
no code implementations • 22 Sep 2021 • Michael Higgins, Dominic Widdows, Chris Brew, Gwen Christian, Andrew Maurer, Matthew Dunn, Sujit Mathi, Akshay Hazare, George Bonev, Beth Ann Hockey, Kristen Howell, Joe Bradley
Automatic dialog systems have become a mainstream part of online customer service.
no code implementations • 20 Sep 2021 • Dominic Widdows, Chris Brew
The key finding for language classification is that ranked lists of words and frequencies of characters form a sufficient and robust representation of the regularities of key languages and their orthographies.
no code implementations • ACL (SemSpace, IWCS) 2021 • Dominic Widdows, Kristen Howell, Trevor Cohen
The second considers whether semantic vector composition should be explicitly described mathematically, or whether it can be a model-internal side-effect of training a neural network.
no code implementations • 12 Jan 2021 • Dominic Widdows, Kirsty Kitto, Trevor Cohen
In the decade since 2010, successes in artificial intelligence have been at the forefront of computer science and technology, and vector space models have solidified a position at the forefront of artificial intelligence.
no code implementations • CONLL 2018 • Trevor Cohen, Dominic Widdows
Word order is clearly a vital part of human language, but it has been used comparatively lightly in distributional vector models.