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

Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, Sonal Gupta

Abstract
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.
Anthology ID:
2021.eacl-main.87
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1009–1021
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.eacl-main.87/
DOI:
10.18653/v1/2021.eacl-main.87
Bibkey:
Cite (ACL):
Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, and Sonal Gupta. 2021. El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1009–1021, Online. Association for Computational Linguistics.
Cite (Informal):
El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing (Einolghozati et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.eacl-main.87.pdf
PDF Search Fix metadata