Speaking to personal conversational assistants such as Amazon Alexa and Google Assistant has become a reality for many. How can we use these apps? How can we create new apps to do the tasks we want them to do? Learn about new applications and research in spoken language technology.
Keynote talk at ESSV2018, Ulm, Germany.
Paper: Conversation modelling for chatbots: current approaches and future directions. In Berton, A., Haiber, U. and Minker, W. (eds) Elektronishce Sprachsignalverarbeitung 2018, Tagungsband der 29. Konferenz, Ulm, 7-9 March 2018, TUDpress, pp.175-185.
SpeechTEK2018, Washington DC, USA, 9-11 April, 2018.
Monday, April 9, 2018. Intro to Intelligent Assistants.
Intelligent assistants are part of our daily lives, thanks to recent advances in artificial intelligence and spoken language technology. How can we make these assistants interact successfully with us? View a short demo of how to build a simple interaction. Learn about the basic concepts—skills, intents, and entities. Consider the importance of extensive training and testing and what we can learn from the experiences of a generation of voice user interface designers.
Tuesday, April 10, 2018. Tuesday Knowledge Cafe (Sunrise session).
Tuesday, April 10, 2018. Modeling conversation for chatbots.
The major intelligent agent platforms have converged on terminology involving intent identification and entity extraction, yet use different conversational models to describe behavior. Learn how these conversational models differ and which go beyond hard-coded conversation flows of “happy path” dialogues to model conversational phenomena such as follow-up questions, changes of topic, out-of-scope utterances, and other types of edge case. What are the desiderata for intelligent conversational agents?
Wednesday, April 11. Workshop: Build a conversational chatbot for Google Assistant.
Google Assistant allows users to engage with information and services through devices such as Google Home, Android smartphones and iPhones, and, ultimately, a wide range of other smart devices. Creating a conversational chatbot brings certain challenges. This tutorial begins by exploring issues of conversation design and then outlines the various tools available, such as Actions on Google, which supports the building of apps for Google Assistant; API.AI (Dialogflow), a tool for defining the natural language understanding and dialogue components of a conversation; Google templates, an alternative way to quickly create a conversational app; and Actions Simulator, a tool for testing the chatbot. The main part of the tutorial provides a hands-on demonstration of the tools.
32nd Human Computer Interaction Conference, Belfast, Northern Ireland, 2-6 July, 2018 .
2 July, 2018. Masterclass tutorial: Designing and developing a conversational chatbot.
Keynote: Chatbots as a new interface to smart devices: issues and challenges.
Natural Language ProcessingWe can provide advice and consultancy in many areas that make use of speech and language technologies
A VoiceXML application enables users to obtain information and services on the Internet by simply speaking on their landline telephone or mobile device.
Developers specify a VoiceXML application using a markup language similar to HTML. In this way developers can build on the existing Web infrastructure using standard Internet protocols.
Vast amounts of natural language text are produced daily and stored on computers, ranging from emails, blogs, and social media messages to newspaper stories and scientific articles.
Natural Language Processing researchers have developed methods to process this text and to make use of it in a variety of interesting and useful ways.
Spoken natural language is becoming a natural and intuitive mode of communication with our hand-held mobile devices
For more information about how you could benefit from natural language processing, send an email to:
In collaboration with the University of Ulster (Ulster) and the South Eastern Health and Social Care Trust we have developed voice-based systems to support home-based monitoring of conditions such as Type 2 Diabetes.Click here for more information.
We are currently investigating ways to extend this technology to other aspects of healthcare.
To find out more, send an email to: