A group of researchers at Osaka University has developed a new method for dialogue systems*1. This new method, lexical acquisition through implicit confirmation, is a method for a computer to acquire the category of an unknown word over multiple dialogues by confirming whether or not its predictions are correct in the flow of conversation.
Many conversation robots, chatbots, and voice assistant apps have appeared in recent years; however, in these systems, computers basically answer questions based on what has been preprogrammed. There is another method in which a computer learns from humans by asking simple repetitive questions; however, if the computer asks only questions such as “What is xyz?” in order to acquire knowledge, users will lose interest in talking with the computer.
The group led by Professor Komatani developed an implicit confirmation method by which the computer acquires the category of an unknown word during conversation with humans. This method aims for the system to predict the category of an unknown word from user input during conversation, to make implicit confirmation requests to the user, and to have the user respond to these requests. In this way, the system acquires knowledge about words during dialogues.
In this method, the system decides whether the prediction is correct or not by using the user response following each request, its context, by using machine learning*2 techniques. In addition, this system’s decision performance improved by taking the classification results gained from dialogues with other users into consideration.
Chatbots in the market speak to anyone in the same manner. However, as dialogue systems become popular in the future, computers will be required to speak by learning from a conversational partner according to the situation. This group’s research results are a new approach towards the realization of dialogue systems in which a computer can become smarter through conversation with humans and will lead to the development of dialogue systems with the ability to customize responses to the user’s situation.
This research project was conducted as a part of joint research with Honda Research Institute Japan Co., Ltd.
*1 Dialogue system
A dialogue system (or conversational system), a part of artificial intelligence, is a computer system intended to converse with a human in natural language. Many speech-enabled IVR (interactive voice response) applications, humanoid robots, and text-based chatbots have been developed in recent years.
*2 Machine learning (AI)
Machine Learning is a method using algorithms to analyze data, learn from it, and then make a determination or prediction. Machine learning includes supervised learning, unsupervised learning, and reinforcement learning. In supervised learning, the computer is trained with a set of examples (dataset) that contains the correct answer; through which it becomes able to make judgements in different situations.
The Latest on: Dialogue systems
- The Lack of Dialogue Between Palestinians and Israelis.on June 25, 2020 at 7:13 pm
For decades there has been an ongoing political conflict between Israel and the occupied Palestinian territories, its solution still seems to be far away.
- US accepts EU offer to create dialogue on China: Pompeoon June 25, 2020 at 3:18 pm
Mechanism will discuss 'concerns we have about the threat China poses to the West and our shared democratic ideals' - Anadolu Agency ...
- COVID-19 Potentially Greatest Threat to South Sudan's Already Fragile Health System, Special Representative Warns Security Councilon June 24, 2020 at 1:14 pm
English News and Press Release on South Sudan about Food and Nutrition, Health, Children, IDPs, Drought, Epidemic and more; published on 24 Jun 2020 by UN SC ...
- Putin: Russia open for dialogue on creating reliable global security systemon June 24, 2020 at 1:07 am
The countries can protect the world "against new dangerous threats" only if they act together, the Russian leader said ...
- Leadership Excellence: Fostering Human Connection And Dialogueon June 22, 2020 at 5:16 am
More than ever, the magnitude of the events flaming across the U.S. requires leadership excellence. Leaders can demonstrate this through their actions by fostering human connection and genuine ...
- Continuing the Conversation: Open and honest dialogue with Lamarcus Joyner and Alec Ingoldon June 19, 2020 at 1:38 pm
Watch as fullback Alec Ingold and safety Lamarcus Joyner speak from the heart about brotherhood, unity and the power of using your voice.
- Texas AD Chris Del Conte: Meeting with football team had 'tremendous' dialogue on topic of diversityon June 18, 2020 at 1:26 pm
Texas athletic director Chris Del Conte said there was "tremendous" dialogue in a meeting involving him, university president Jay Hartzell and the Texas football team Wednesday night.
- Opportunities, challenges in US-Iraqi dialogue – opinionon June 18, 2020 at 9:58 am
Iraq witnessed many transformations and changes during that period, and Iran was the main entity influencing them.
- Missing from the current national dialogue: The youth voiceon June 17, 2020 at 4:22 pm
Alexis Glick, the CEO of GENYOUth, shares new polling data on how teens are coping with COVID-19, and says listening to the concerns of kids is something we don’t do enough of.
- Art and science in dialogue: Schaufler [email protected] Dresden 2021on June 17, 2020 at 8:03 am
Starting in January 2021, the New York artist Anton Ginzburg will begin his six-month residency at TU Dresden as the second fellowship recipient in the Schaufler [email protected] Dresdens artist-in-residence ...
via Google News and Bing News