Weakly-supervised Neural Semantic Parsing with a Generative Ranker
This addresses the challenge of training semantic parsers without explicit logical form annotations, which is incremental as it builds on existing weakly-supervised methods.
The paper tackles the problem of weakly-supervised semantic parsing with a neural parser-ranker system that generates and ranks logical forms using denotation clues and utterance semantics, achieving state-of-the-art results on three Freebase datasets.
Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker system for weakly-supervised semantic parsing. The parser generates candidate tree-structured logical forms from utterances using clues of denotations. These candidates are then ranked based on two criterion: their likelihood of executing to the correct denotation, and their agreement with the utterance semantics. We present a scheduled training procedure to balance the contribution of the two objectives. Furthermore, we propose to use a neurally encoded lexicon to inject prior domain knowledge to the model. Experiments on three Freebase datasets demonstrate the effectiveness of our semantic parser, achieving results within the state-of-the-art range.