Language to Logical Form with Neural Attention
This addresses the challenge of semantic parsing for NLP applications by providing a more general and adaptable method, though it is incremental as it builds on existing encoder-decoder models with attention.
The paper tackled the problem of mapping natural language to logical forms without relying on hand-engineered features, and the result was a competitive performance across four datasets, demonstrating easy adaptation across domains and representations.
Semantic parsing aims at mapping natural language to machine interpretable meaning representations. Traditional approaches rely on high-quality lexicons, manually-built templates, and linguistic features which are either domain- or representation-specific. In this paper we present a general method based on an attention-enhanced encoder-decoder model. We encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors. Experimental results on four datasets show that our approach performs competitively without using hand-engineered features and is easy to adapt across domains and meaning representations.