mlsanityData to 7 Oct 2026

Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing

arXiv 2410.00513 ↗First posted 1 Oct 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent efforts have aimed to utilize multilingual pretrained language models (mPLMs) to extend semantic parsing (SP) across multiple languages without requiring extensive annotations. However, achieving zero-shot cross-lingual transfer for SP remains challenging, leading to a performance gap between source and target languages. In this study, we propose Cross-Lingual Back-Parsing (CBP), a novel data augmentation methodology designed to enhance cross-lingual transfer for SP. Leveraging the representation geometry of the mPLMs, CBP synthesizes target language utterances from source meaning representations. Our methodology effectively performs cross-lingual data augmentation in challenging zero-resource settings, by utilizing only labeled data in the source language and monolingual corpora. Extensive experiments on two cross-language SP benchmarks (Mschema2QA and Xspider) demonstrate that CBP brings substantial gains in the target language. Further analysis of the synthesized utterances shows that our method successfully generates target language utterances with high slot value alignment rates while preserving semantic integrity. Our codes and data are publicly available at https://github.com/deokhk/CBP.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 1 Oct 2024.

Builds on

34 of 46 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  8. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  9. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
  10. 2017Word Translation Without Parallel Datacited by 480
  11. 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 443
  12. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 416
22 more
  1. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  2. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  3. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 167
  4. 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
  5. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  6. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  7. 2022The Geometry of Multilingual Language Model Representationscited by 94
  8. 2020On the Language Neutrality of Pre-trained Multilingual Representationscited by 82
  9. 2019How Language-Neutral is Multilingual BERT?cited by 51
  10. 2020A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamesecited by 36
  11. 2019A Pilot Study for Chinese SQL Semantic Parsingcited by 33
  12. 2022XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsingcited by 32
  13. 2023mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinationscited by 24
  14. 2021ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generationcited by 23
  15. 2021Multilingual Unsupervised Neural Machine Translation with Denoising Adapterscited by 22
  16. 2022CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsingcited by 21
  17. 2021Few-shot Controllable Style Transfer for Low-Resource Multilingual Settingscited by 20
  18. 2021Zero-Shot Cross-lingual Semantic Parsingcited by 19
  19. 2021Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Datacited by 17
  20. 2021A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representationscited by 16
  21. 2021Multilingual Neural Semantic Parsing for Low-Resourced Languagescited by 7
  22. 2023XSemPLR: Cross-Lingual Semantic Parsing in Multiple Natural Languages and Meaning Representationscited by 5

Built on by

Not cited yet.