Conversation as a Platform: How Machine Learning, Natural Language Processing, Knowledge Computing Can Contribute?

Printer-friendly version

When: September 6 2016
Where: Sage 2704
With the availability of personal agents such as Cortana, Siri and Google Now, a world of humans and machines communicate and solve problems together in natural language seems not far away. The scene of freely chatting with HAL in “2001: A Space Odyssey” or Samantha in “Her” could happen to us within our lifetime. The question is: “Are we ready?”, and if the answer is “no”, then we want to ask: “What are the necessary technologies to make it happen? In this talk, I will first give an overview of how machine learning, natural language processing, and knowledge computing research are applied in Microsoft’s conversation as a platform efforts and then use math problem solving as an example to highlight the challenges ahead.

Dr. Lin is a Principal Researcher and Research Manager of the Knowledge Computing group at Microsoft Research Asia. His research interests are knowledge mining, natural language processing, problem solving, question answering, and automatic summarization.

Recently, his main research directions are: (1) developing a knowledge computing framework for real world applications and services including automatic acquisition of semantic knowledge, machine reading for semantic indexing, and automatic understanding of user intents; and (2) developing big social data analytics platform and services – Project Soul. Building on experiences learned from Project Soul, his team is developing technologies to automatically learn social interaction knowledge from large-scale real world online data and transform unstructured and semi-structured web data into structured data to enable semantic computing. The goal is to enable context-aware interactive knowledge-enriched applications powered by intelligent data in the cloud.

He developed automatic evaluation technologies for summarization, QA, and MT. In particular, he created the ROUGE automatic summarization evaluation package. It has become the de facto standard in summarization evaluations. ROUGE has been chosen as the official automatic evaluation package for Document Understanding Conference since 2004.