Research talk: Summarizing information across multiple documents and modalities

Опубликовано 25 января 2022, 1:37

Speaker: Subhojit Som, Principal Applied Science Manager, Microsoft

Search engines have evolved over time, from initially providing the most relevant URLs to user queries to providing information in response to user queries that summarize content from multiple web documents. Instead of clicking and reading the top search results and finding the information themselves, users can now rely on search engines to ""read"" these documents via long document machine reading comprehension techniques and present the relevant summary from various documents to them. With recent breakthroughs in natural language generation and understanding of multi-modality content, search engines can now return very rich information presented in a comprehensive and easy-to-consume way. In this presentation, we will talk about some of the technologies behind this experience and how we see technology evolving in the future.

Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit