Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing

by   Xilun Chen, et al.

Task-oriented semantic parsing is a critical component of virtual assistants, which is responsible for understanding the user's intents (set reminder, play music, etc.). Recent advances in deep learning have enabled several approaches to successfully parse more complex queries (Gupta et al., 2018; Rongali et al.,2020), but these models require a large amount of annotated training data to parse queries on new domains (e.g. reminder, music). In this paper, we focus on adapting task-oriented semantic parsers to low-resource domains, and propose a novel method that outperforms a supervised neural model at a 10-fold data reduction. In particular, we identify two fundamental factors for low-resource domain adaptation: better representation learning and better training techniques. Our representation learning uses BART (Lewis et al., 2019) to initialize our model which outperforms encoder-only pre-trained representations used in previous work. Furthermore, we train with optimization-based meta-learning (Finn et al., 2017) to improve generalization to low-resource domains. This approach significantly outperforms all baseline methods in the experiments on a newly collected multi-domain task-oriented semantic parsing dataset (TOPv2), which we release to the public.


page 1

page 2

page 3

page 4


Neural Structural Correspondence Learning for Domain Adaptation

Domain adaptation, adapting models from domains rich in labeled training...

Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation

We introduce a novel setup for low-resource task-oriented semantic parsi...

Normalizing Compositional Structures Across Graphbanks

The emergence of a variety of graph-based meaning representations (MRs) ...

A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese

Semantic parsing is an important NLP task. However, Vietnamese is a low-...

X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing

Task-oriented compositional semantic parsing (TCSP) handles complex nest...

Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling

Task-oriented semantic parsing models typically have high resource requi...

Self-Training for Unsupervised Parsing with PRPN

Neural unsupervised parsing (UP) models learn to parse without access to...