El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing

by   Arash Einolghozati, et al.

Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales. In this work, we focus on Spanglish (Spanish+English) and release a dataset, CSTOP, containing 5800 CS utterances alongside their semantic parses. We examine the CS generalizability of various Cross-lingual (XL) models and exhibit the advantage of pre-trained XL language models when data for only one language is present. As such, we focus on improving the pre-trained models for the case when only English corpus alongside either zero or a few CS training instances are available. We propose two data augmentation methods for the zero-shot and the few-shot settings: fine-tune using translate-and-align and augment using a generation model followed by match-and-filter. Combining the few-shot setting with the above improvements decreases the initial 30-point accuracy gap between the zero-shot and the full-data settings by two thirds.


page 1

page 2

page 3

page 4


Translate Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

While multilingual pretrained language models (LMs) fine-tuned on a sing...

Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsing

Deep learning methods have enabled task-oriented semantic parsing of inc...

Zero-Shot Cross-lingual Semantic Parsing

Recent work in crosslingual semantic parsing has successfully applied ma...

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

Building dialogue generation systems in a zero-shot scenario remains a h...

On the Relation between Syntactic Divergence and Zero-Shot Performance

We explore the link between the extent to which syntactic relations are ...

Multilingual Compositional Wikidata Questions

Semantic parsing allows humans to leverage vast knowledge resources thro...

Multinational Address Parsing: A Zero-Shot Evaluation

Address parsing consists of identifying the segments that make up an add...