no code implementations • 15 Jan 2024 • Steve Battle
We present a novel form of Liquid Automata, using this to simulate autopoiesis, whereby living machines self-organise in the physical realm.
no code implementations • 11 Sep 2022 • Reece Nicholls, Ryan Fellows, Steve Battle, Hisham Ihshaish
IT helpdesks are charged with the task of responding quickly to user queries.
no code implementations • 21 Dec 2021 • Ryan Fellows, Hisham Ihshaish, Steve Battle, Ciaran Haines, Peter Mayhew, J. Ignacio Deza
Task-oriented dialogue systems (TODS) are continuing to rise in popularity as various industries find ways to effectively harness their capabilities, saving both time and money.
1 code implementation • Natural Language Engineering 2021 • Nathan Duran, Steve Battle, Jim Smith
In this study, we investigate the process of generating single-sentence representations for the purpose of Dialogue Act (DA) classification, including several aspects of text pre-processing and input representation which are often overlooked or underreported within the literature, for example, the number of words to keep in the vocabulary or input sequences.
1 code implementation • Engineering Applications of Neural Networks 2018 • Nathan Duran, Steve Battle
The identification of Dialogue Act’s (DA) is an important aspect in determining the meaning of an utterance for many applications that require natural language understanding, and recent work using recurrent neural networks (RNN) has shown promising results when applied to the DA classification problem.
Ranked #1 on Dialog Act Classification on Switchboard dialogue act corpus (Accuracy (%) metric)