Consumers today have been frustrated by the current crop of chatbots that have clunky menus to navigate through, and a limited ability to respond to questions users asked. Lex can actually work in any voice or text chatbot on mobile, web or in other chat services beyond Messenger, including Slack and Twilio SMS.Īmazon has suggested it could be used for a variety of purposes, including web and mobile applications where the technology provides users with information, powers their application, helps with various work activities, or even provides a control mechanism for robots, drones and toys.Ĭhatbots in messaging – and particularly in e-commerce bots – is a solid entry point for Lex’s technology, though. However, the system is not limited to working only in the chatbots you find in today’s consumer messaging apps, like Facebook Messenger (though it can be integrated with that platform). The system, which involves natural language understanding technology combined with automatic speech recognition, was first introduced in November, at Amazon’s AWS re:Invent conference in Las Vegas.Īt the time, Amazon explained how Lex can be used by developers who want to build their own conversational applications, like chatbots.Īs an example, the company had demoed a tool that allowed users to book a flight using only their voice. The team has published a technical white-paper about their work, Emora: An Inquisitive Social Chatbot Who Cares For You.Amazon Lex, the technology powering Amazon’s virtual assistant Alexa, has exited preview, according to a report from Reuters this morning.
“A chatbot could potentially help them gain confidence and improve their mood so they could better engage with people.” “People with depression often try to avoid talking to others and may become socially isolated,” Choi told the university publication. “We are currently re-engineering our models to make them lighter so we can integrate them into our next version of Emora.”Ī longer-term goal of the team is to develop a chatbot that can help people with depression or mental health challenges. “Practically, all our research uses NVIDIA GPUs to develop deep learning-based NLP models,” Choi said.
On the training side, the team used NVIDIA GPUs with PyTorch, TensorFlow, and MXNet. We had components that encouraged people to talk about their family members and to keep in touch with them as much as possible.” “We also wanted to support human relations, especially family relations. We aimed to satisfy people,” Jinho Choi, assistant professor in the Department of Computer Science, told Emory News. We didn’t set out to design technology that would impress people. “From the beginning, our team slogan has been ‘Emora cares for you. The success rate was measured by user ratings and how long users continued the conversations. The components included an intent-topic classifier, a response ranker, semantic parsing, coreference resolution, and event extraction models. To develop the tool the team developed a variety of deep learning models to boost the system’s accuracy. This is the third year in a row the Emory team has won the Alexa prize in terms Launched in 2016, the Alexa prize challenges students to make breakthroughs in the design of chatbots. “We designed a more socially oriented chatbot that could actually show interest in an individual user and provide comfort to people if they wanted it.” Jinho Choi (center), the faculty advisor for the Emory Alexa Prize team, with graduate students James Finch (left), and Sarah Fillwock, the team leader. “Normally people think of a chatbot as being an intelligent assistant, to answer questions or provide customer service,” graduate student Sarah Fillwock told the Emory News Center. Emora can chat about movies, sports, news of the day, or concerns they might have about themselves or their families during the COVID-19 pandemic. The researchers developed Emora as a social companion that can provide comfort and warmth to people interacting with Alexa-enabled devices. The team earned $500,000 for their chatbot named Emora.
A team of Emory University students won Amazon’s 2020 Alexa Socialbot Grand Challenge, a worldwide competition to create that most engaging AI chatbot.
0 kommentar(er)
