Improving Semantic Parsing for Task Oriented Dialog

Abstract

Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results [Gupta et al 2018]. In this paper, we present three different improvements to the model: contextualized embeddings, ensembling, and pairwise re-ranking based on a language model. We taxonomize the errors possible for the hierarchical representation, such as wrong top intent, missing spans or split spans, and show that the three approaches correct different kinds of errors. The best model combines the three techniques and gives 6.4% better exact match accuracy than the state-of-the-art, with an error reduction of 33%, resulting in a new state-of-the-art result on the Task Oriented Parsing (TOP) dataset.

References in corpus (2)

• Language to Logical Form with Neural Attention
• Learning Structured Natural Language Representations for Semantic Parsing

Cited by in corpus (7)

• DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue
• Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling
• Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing
• Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
• A Pilot Study for Chinese SQL Semantic Parsing
• Using multiple ASR hypotheses to boost i18n NLU performance
• Assessing Data Efficiency in Task-Oriented Semantic Parsing