Information-seeking Conversational System
Overview
Our invention helped to leverage AI-enabled natural language processing technologies to find relevant information from massive documents and make responses to user queries.
Technical name of innovation
Information-seeking Conversational System
Commercialisation opportunities
non-exclusive licensing
Problem addressed
For most knowledge bases, there is a vast amount of document content to communicate with human readers for sharing knowledge. Making the document content accessible to users via conversational systems could be a meaningful yet challenging task.
Innovation
- To effectively improve the accuracy of information retrieval and response generation, our team proposed a pipeline system of "retrieve, re-rank, and generate" for handling users' information-seeking queries.
Key impact
- This invention can automatically retrieve some relevant information from massive documents, and then generate answers in response to users' queries .
- This invention can continuously complete user requests in the form of a user-friendly conversational chatbot.
- This invention helps to advance AI-enabled information seeking technologies, reducing the costs for users to search information.
Award
- First place in ACL 2022 DialDoc Shared Task Competition
- Information of the award: https://cpii.hk/2022/06/01/award-dialdocacl-2022-challenge/
Application
- This conversational chatbot can help users to search for information from massive contents ranging from encyclopedias to public policies.
Patent
- US-Provisional Patent:17900806
Centre for Perceptual and Interactive Intelligence was established by The Chinese University of Hong Kong in 2020. Our Centre Director Professor Helen Meng and Principal Investigators have rich backgrounds in computer vision, multilingual speech and language technologies, natural language processing, and AI-enabled design automation.
Enquiry
