Join us for one of our weekly tech talks to learn more about our software engineering teams. This week, Gautam Shine will discuss Learning the Lexicon of Financial Markets to Understand Natural Language Queries.
Learning the Lexicon of Financial Markets to Understand Natural Language Queries
Question answering (QA) requires computers to understand and act upon queries from humans. The process of transforming natural language into precise and executable meaning representations is known as semantic parsing. Can we induce a semantic parser from data using machine learning? The challenge lies in blending the symbolic and statistical sides of AI while retaining the accuracy levels required in finance.
In this talk, we will introduce our research into learning grammars for financial QA in collaboration with Prof. Yoav Artzi of Cornell University. We utilize the combinatory categorial grammar (CCG) framework, which aligns syntax (functions of parts of speech) and semantics (typed lambda calculus). We will assess the challenges of learning and inference in this approach and compare it to other semantic parsing methods.