Ice Pasupat “Natural Language Interface for Web Interaction via Compositional Generation”
Talk: Panupong (Ice) Pasupat
Title: “Natural Language Interface for Web Interaction via Compositional Generation”
Natural language understanding models have achieved good enough performance for commercial products such as virtual assistants. However, their scopes are mostly still limited to preselected domains or simpler sentences. I will present my line of work which extends natural language understanding in two frontiers: handling open-domain environments such as the Web (breadth) and handling complex sentences (depth).
The presentation will focus on the task of answering complex questions on semi-structured Web tables using question-answer pairs as supervision. Within the framework of semantic parsing, which is to learn to parse sentences into executable logical forms, I will explain our proposed methods to (1) flexibly handle lexical and syntactic mismatches between the questions and logical forms, (2) filter misleading logical forms that sometimes give correct answers, and (3) reuse parts of good logical forms to make training more efficient. I will also briefly mention how these ideas can be applied to several other natural language understanding tasks for Web interaction.
Panupong (Ice) Pasupat is a PhD candidate in Stanford NLP group supervised by Percy Liang. Ice’s main research interests include semantic parsing, question answering, and dialog systems. Ice’s research theme is to use the Web as an environment: the Web is a messy and thus challenging environment for language understanding, while at the same time agents for Web interaction have many potential applications that can facilitate people’s lives.
We hope you will enjoy this and some our 14k+ other artificial intelligence videos. We keep adding new channels and playlists all the time, so the number of fresh videos keeps growing every day.
BTC 3KqW2c7wrhJDxAjBaywzj74mF2u5uZg665 (get a BTC wallet, get free BTC)