mlsanityData to 14 Oct 2026

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

arXiv 2101.10524 ↗First posted 26 Jan 2021cs.CL cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 26 Jan 2021.

Builds on

34 of 56 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  7. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  8. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  9. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  10. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  11. 2019How multilingual is Multilingual BERT?cited by 645
  12. 2017Word Translation Without Parallel Datacited by 487
22 more
  1. 2019BERT for Joint Intent Classification and Slot Fillingcited by 196
  2. 2020Data Augmentation using Pre-trained Transformer Modelscited by 168
  3. 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 125
  4. 2020Multilingual Alignment of Contextual Word Representationscited by 114
  5. 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
  6. 2014Grammar as a Foreign Languagecited by 70
  7. 2019Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsingcited by 70
  8. 2020Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsingcited by 59
  9. 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
  10. 2019Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsingcited by 46
  11. 2019Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systemscited by 42
  12. 2019XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answeringcited by 35
  13. 2019Overview for the Second Shared Task on Language Identification in Code-Switched Datacited by 33
  14. 2019Entity Projection via Machine Translation for Cross-Lingual NERcited by 32
  15. 2018Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentationcited by 26
  16. 2019Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Taskcited by 24
  17. 2018Universal Dependency Parsing for Hindi-English Code-switchingcited by 18
  18. 2019Context-Aware Cross-Lingual Mappingcited by 17
  19. 2016Shallow Parsing Pipeline for Hindi-English Code-Mixed Social Media Textcited by 7
  20. 2017Joining Hands: Exploiting Monolingual Treebanks for Parsing of Code-mixing Datacited by 7
  21. 2019Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognitioncited by 7
  22. 2018PyText: A Seamless Path from NLP research to productioncited by 3

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 4; 2023: 1.

8 papers.

  1. 2021From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understandingcited by 43
  2. 2021Zero-Shot Cross-lingual Semantic Parsingcited by 19
  3. 2022A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialogcited by 14
  4. 2022CST5: Data Augmentation for Code-Switched Semantic Parsingcited by 5
  5. 2023Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Datacited by 4
  6. 2021Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Modelscited by 2
  7. 2022DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialoguecited by 1
  8. 2022Automatic Identification of Motivation for Code-Switching in Speech Transcriptscited by 1