Improving Sequence-to-Sequence Semantic Parser for Task Oriented Dialog

Task Oriented Parsing (TOP) attempts to map utterances to compositional requests, including multiple intents and their slots. Previous work focus on a tree-based hierarchical meaning representation, and applying constituency parsing techniques to address TOP. In this paper, we propose a new format of meaning representation that is more compact and amenable to sequence-to-sequence (seq-to-seq) models. A simple copy-augmented seq-to-seq parser is built and evaluated over a public TOP dataset, resulting in 3.44% improvement over prior best seq-to-seq parser (exact match accuracy), which is also comparable to constituency parsers’ performance.