New method allows computers to learn unknown words

Scientists have developed a novel technique that allows computers to learn new words during conversation with humans.
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, researchers said.
The method developed by researchers at Osaka University in Japan 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, researchers said.

The system decides whether the prediction is correct or not by analysing the user response following each request by using machine learning 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, researchers said.
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, they said.
The group's research results are a new approach towards the realisation 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 customise responses to the user's situation.