Related papers: Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

URL: http://arxiv.org/abs/2001.11458v1
Date: Thu, 30 Jan 2020 17:11:00 GMT
Title: Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing
Authors: Subendhu Rongali (University of Massachusetts Amherst), Luca Soldaini (Amazon Alexa Search), Emilio Monti (Amazon Alexa), Wael Hamza (Amazon Alexa AI)
Abstract summary: Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. We propose a unified architecture based on Sequence to Sequence models and Pointer Generator Network to handle both simple and complex queries.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical slot-filling systems have been used to parse "simple" queries; that is, queries that contain a single action and can be decomposed into a set of non-overlapping entities. More recently, shift-reduce parsers have been proposed to process more complex utterances. These methods, while powerful, impose specific limitations on the type of queries that can be parsed; namely, they require a query to be representable as a parse tree. In this work, we propose a unified architecture based on Sequence to Sequence models and Pointer Generator Network to handle both simple and complex queries. Unlike other works, our approach does not impose any restriction on the semantic parse schema. Furthermore, experiments show that it achieves state of the art performance on three publicly available datasets (ATIS, SNIPS, Facebook TOP), relatively improving between 3.3% and 7.7% in exact match accuracy over previous systems. Finally, we show the effectiveness of our approach on two internal datasets.