id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_hn3zcuyx55c5hluvhowvnqdplm	Yoav Artzi	Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions	2013	14	.pdf	application/pdf	8825	910	64	approach that learns a joint model of meaning and context for interpreting and executing Correct interpretation requires us to solve many subproblems, such as resolving all referring expressions to specific objects in the environment (including, "the corner" or "the third intersection"), disambiguating word sense based on context (e.g., "the To model complex instructional language, we introduce a new semantic modeling approach that can represent a number of key linguistic a start state s ∈ S and a natural language instruction x, we aim to generate a sequence of actions CCG parse builds a logical form for a complete sentence in our example navigation domain. state s, validation function V, lexicon λ and model parameters θ, and returns a set of lexical entries, as defined in Section 8. semantic parser that includes a joint model of meaning and context for executing natural language instructions.	./cache/work_hn3zcuyx55c5hluvhowvnqdplm.pdf	./txt/work_hn3zcuyx55c5hluvhowvnqdplm.txt