Technique to allow AI to learn words in the flow of dialogue developed

December 26, 2017

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.

This research, entitled Lexical Acquisition through Implicit Confirmations over Multiple Dialogues, was presented at SIGDIAL 2017, 18th Annual SIGdial Meeting on August 17, 2017.

Authors: Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano and Kazunori Komatani

Osaka University

Related Computer Articles from Brightsurf:

UCLA computer scientists set benchmarks to optimize quantum computer performance
Two UCLA computer scientists have shown that existing compilers, which tell quantum computers how to use their circuits to execute quantum programs, inhibit the computers' ability to achieve optimal performance.

Digitize your dog into a computer game
Researchers from CAMERA at the University of Bath have developed motion capture technology that enables you to digitise your dog without a motion capture suit and using only one camera.

Stabilizing brain-computer interfaces
Researchers from Carnegie Mellon University (CMU) and the University of Pittsburgh (Pitt) have published research in Nature Biomedical Engineering that will drastically improve brain-computer interfaces and their ability to remain stabilized during use, greatly reducing or potentially eliminating the need to recalibrate these devices during or between experiments.

Computer-generated genomes
Professor Beat Christen, ETH Zurich to speak in the AAAS 2020 session, 'Synthetic Biology: Digital Design of Living Systems.' Christen will describe how computational algorithms paired with chemical DNA synthesis enable digital manufacturing of biological systems up to the size of entire microbial genomes.

Computer-based weather forecast: New algorithm outperforms mainframe computer systems
The exponential growth in computer processing power seen over the past 60 years may soon come to a halt.

A computer that understands how you feel
Neuroscientists have developed a brain-inspired computer system that can look at an image and determine what emotion it evokes in people.

Computer program looks five minutes into the future
Scientists from the University of Bonn have developed software that can look minutes into the future: The program learns the typical sequence of actions, such as cooking, from video sequences.

Computer redesigns enzyme
University of Groningen biotechnologists used a computational method to redesign aspartase and convert it to a catalyst for asymmetric hydroamination reactions.

Mining for gold with a computer
Engineers from Texas A&M University and Virginia Tech report important new insights into nanoporous gold -- a material with growing applications in several areas, including energy storage and biomedical devices -- all without stepping into a lab.

Teaching quantum physics to a computer
An international collaboration led by ETH physicists has used machine learning to teach a computer how to predict the outcomes of quantum experiments.

Read More: Computer News and Computer Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to