Institute of Information Science, Academia Sinica

We encounter various kinds of data in daily life, for example, weather conditions, game results, product specifications, physical examination results, stock performance, financial data, etc. How to describe, summarize and communicate these data in effective and appropriate manner become necessary. In this talk, I will introduce an automatic text generation project Data2Text, major challenges in text generation, possible solutions, evaluation issues, and demonstrate how Data2Text works.

Dr. Lin is the group manager of the Knowledge Computing group at Microsoft Research Asia. His research interests are knowledge computing, natural language processing, semantic search, and text generation with two major main research directions: (1) automatic text generation from structured data, developing models and algorithms to acquire writing and speaking knowledge automatically from massive data; and (2) grounded semantic computing, developing semantic computing framework for real world applications and services including automatic acquisition of semantic knowledge, machine reading for semantic indexing, automatic understanding of user intents, and problem solving.