Extra SEA: Conversational A.I. and Search


We're proud to announce an extra SEA meetup with two very special speakers.

This Wednesday: Jeff Dalton from the University of Glasgow (previously Google) will talk about conversational search and Gary Ren an applied researcher at Microsoft will cover conversational question understanding.

This is a unique opportunity as both speakers are only in Amsterdam for ICTIR (http://sigir.org/ictir2017/), don't miss it!

This edition of SEA will be held in at Science Park 904 in Room C0.05.


16:00 - 16:30 Jeff Dalton

16:30 - 17:00 Gary Ren

17:00 - 18:00 Drinks & Snacks

Details of the talks:


Jeff Dalton - Research Challenges in Conversational Search

The recent rise of virtual personal assistants such as the Google Assistant, Alexa, Cortana, and Siri promises a new generation of AI-driven search systems. These agents provide a new interactive natural language interface that allows users to interact with information and performs actions in the world. This talk will present an overview of the current research challenges including: semantic parsing, personal knowledge graphs, conversational question answering, result distillation, interactive feedback, and evaluation.

Jeff is a Lecturer in the School of Computing at the University of Glasgow. Previously, he worked at Google on the Assistant Natural Language Understanding and Knowledge Discovery teams. He completed his PhD at the University of Massachusetts Amherst with James Allan in the Center for Intelligent Information Retrieval. His research focuses on the intersection of Information Retrieval and Natural Language Understanding.


Gary Ren - Conversational Question Understanding Using Web Knowledge

Existing research on question understanding and answering have focused on standalone questions. However, as interactions between humans and machines become increasingly conversational, there is a need for understanding conversational/multiturn questions, defined here as questions that depend on the context of the current conversation. This presentation will introduce a novel architecture that leverages NLP techniques, deep learning, and search engine web knowledge to understand these multiturn questions by reformulating them into standalone questions that a downstream information retrieval system/dialogue agent expects. This presentation will also briefly explore the benefits of having a search powered system that can have guided conversations with users.

Gary is an applied scientist at Microsoft AI and Research on the Bing Core Relevance team; currently working on conversational search, question understanding, and question answering. Look forward to meeting all of you at the meetup!