We present Tranx, a transition-based neu-ral semantic parser that maps natural language (NL) utterances into formal meaning repre-sentations (MRs). Tranx uses a transition system based on the abstract syntax descrip-tion language for the target MR, which gives it two major advantages: (1) it is highly ac-curate, using information from the syntax of the target MR to constrain the output space and model the information flow, and (2) it is highly generalizable, and can easily be applied to new types of MR by just writing a new ab-stract syntax description corresponding to the allowable structures in the MR. Experiments on four different semantic parsing and code generation tasks show that our system is gen-eralizable, extensible, and effective, register-ing strong results compared to existing neural semantic parsers.
展开▼
