Leading travel aggregator and booking engine required highly accurate datasets for a booking assistant BOT that operates in multiple languages
CHALLENGE A leading travel aggregator and booking engine required data to train its AI platform that powers its booking assistant chatbot. The chatbot needed to accurately identify the intent of customer messages in order to seamlessly provide the appropriate response to the customer messages and questions about specific hotels, hotel chains, and locations around the world. The chatbot also had to be able to respond to questions in multiple languages. IMPROVED NET-PROMOTER SCORE RESULTS SOLUTION To reach the seamless performance expected by the travel aggregator and its customers, the chatbot needed to be trained for a large number of utterances per intent in English, Chinese, and French. To achieve this the Innodata team annotated incoming chatbot messages for any mention of specific hotels, occurrences of locations, including cities, regions, districts, and addresses, and categorize the intent of the utterances based on their subjective interpretation of the message. This process of annotating utterances and assigning labels from a taxonomy allowed the Chatbot to understand customer intent from incoming messaging and provide relevant and accurate responses. To ensure the accuracy and quality of the annotations, the Innodata team utilized a double-blind pass process, in which two different annotators provide annotations and an adjudicator provides a judgement on any discrepancies between the annotations. IMPACT The travel aggregator received highly accurate annotated and labeled datasets which enabled the booking assistant AI chatbot to appropriately respond to customer messages and inquiries with relevant information in multiple languages improving the net promoter score.