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

By Subendhu Rongali, Luca Soldaini, Emilio Monti, Wael Hamza. 2020

100 citations recorded by the source corpus.

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.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Autoregressive Entity Retrieval (2020, background): “…NLP tasks with a structured input or output into sequence-to-sequence problems has been explored for different problems, including semantic parsing (Rongali et al., 2020), semantic role labelling (Daza & Frank, 2018), discourse representation structure parsing (Liu et al., 2018), generation of…”
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, background): “Therefore, semantic parsers are widely adopted in dialogue systems to map natural language (NL) utterances to executable programs or logical forms ∗corresponding author (LFs) (Damonte et al., 2019; Rongali et al., 2020).”
MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark (2020, methodology): “Although, there have been sizable efforts around developing successful semantic parsing models for task-oriented dialog systems in English (Mesnil et al., 2013; Liu and Lane, 2016; Gupta et al., 2018; Rongali et al., 2020), we have only seen limited works for other languages.”
MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages (2022, methodology): “demonstrated using sequence-to-sequence models and pointer networks (Rongali et al., 2020).”
Structured Prediction as Translation between Augmented Natural Languages (2021, background): “…is also related to previous works that use seq2seq approaches to perform parsing (Vinyals et al., 2015; Dyer et al., 2016; Choe & Charniak, 2016; Rongali et al., 2020), with the main difference that we propose a general framework that uses augmented natural languages as a way to unify multiple…”
DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue (2020, methodology): “On the TOP dataset, the best models use sophisticated architectures which have been tailored to the task of semantic parsing (Einolghozati et al., 2019; Rongali et al., 2020).”
ReasonBERT: Pre-trained to Reason with Distant Supervision (2021, background): “…knowledge about language and signiﬁcantly boost model performance on a wide range of downstream tasks (Liu et al., 2019a; Wang et al., 2019a,b) ranging from spell checking (Awasthi et al., 2019) to sentiment analysis (Xu et al., 2019) and semantic parsing (Rongali et al., 2020), just to name a few.”
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey (2021, background): “Casting a problem into an index generation task is also proposed for semantic parsing (i.e., filling slots) [152].”