Alibaba makes progress with natural language processing tech

Alibaba’s DAMO Academy Language Technology Lab is laying claim to a deep learning model that scored higher than a human and other competitors during a Q&A task in Microsoft’s machine reading comprehension test, MS MARCO.

Its natural language processing (NLP) technology is already being used in Alibaba’s e-commerce platforms. For example, during a Lazada promotion event last year, the chatbot system supported by the technology achieved a 96% accuracy rate in answering customer inquiries. In the build up, it took just 30 milliseconds for the chatbot to learn all the rules in 25 promotional item sales in Indonesian.

Dr. Luo Si, Leader of the Alibaba DAMO Academy Language Technology Lab, comments: “We are thrilled by the rapid development of NLP over the past year and the exciting prospects of the technology in real life uses. NLP has been a core technology that underpins Alibaba’s business for serving hundreds of millions of customers on our e-commerce platforms including Taobao, Tmall and Lazada.”

“Moving forward, we plan to put NLP on our cloud computing platform Alibaba Cloud, so more clients especially businesses in retail, tourism and public services that involves Q&A tasks could benefit from the technology. We are also exploring a multi-module model that combines features of NLP, speech AI and machine translation. With such a model, users with different languages can communicate more freely with eachother and interact with the machine in real-time without language barriers.”