Sentence Rewriting for Semantic Parsing
This work addresses a specific challenge in semantic parsing for natural language processing applications, but it is incremental as it builds on existing methods with modest improvements.
The paper tackled the vocabulary mismatch problem in semantic parsing by proposing sentence rewriting methods to align natural language with target ontology structures, achieving a 3.4% F1 gain on the WEBQUESTIONS dataset.
A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology. In this paper, we propose a sentence rewriting based semantic parsing method, which can effectively resolve the mismatch problem by rewriting a sentence into a new form which has the same structure with its target logical form. Specifically, we propose two sentence-rewriting methods for two common types of mismatch: a dictionary-based method for 1-N mismatch and a template-based method for N-1 mismatch. We evaluate our entence rewriting based semantic parser on the benchmark semantic parsing dataset -- WEBQUESTIONS. Experimental results show that our system outperforms the base system with a 3.4% gain in F1, and generates logical forms more accurately and parses sentences more robustly.