Conversational systems have improved dramatically recently and are gaining adoption in industries such as e-commerce, banking, finance and real estate to name a few. Although there is a lot of reserach done in developing conversational systems spanning areas such as dialogue systems, NLP, NLU, HCI, search and recommender systems; there are additional challenges when a product is created based on conversational systems and deployed to real world users. Research from different areas come together when convers
Abstract: In this talk, we survey the finance ecosystem and the history of chat and dialog technology used for trading. We discuss the importance of conversation modeling in assisting traders and in tracking compliance. Then, we discuss some complexities of modeling trading conversations, as well as our work on entity recognition and slot filling, intent recognition and conversation disentanglement.
Dr. Amanda Stent works on text analytics and discourse processing as NLP architect at Bloomberg LP. Previously she has held positions as Director, Research and Principal Research Scientist at Yahoo, as Principal Member of Technical Staff at AT&T Labs — Research, and as associate professor in the Computer Science Department at Stony Brook University in Stony Brook, NY. She holds a Ph.D. in computer science from the University of Rochester. She has authored over 90 papers on natural language processing and is