mlsanityData to 7 Oct 2026

Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages

arXiv 2305.14949 ↗First posted 24 May 2023cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes a framework to address the issue of data scarcity in Document-Grounded Dialogue Systems(DGDS). Our model leverages high-resource languages to enhance the capability of dialogue generation in low-resource languages. Specifically, We present a novel pipeline CLEM (Cross-Lingual Enhanced Model) including adversarial training retrieval (Retriever and Re-ranker), and Fid (fusion-in-decoder) generator. To further leverage high-resource language, we also propose an innovative architecture to conduct alignment across different languages with translated training. Extensive experiment results demonstrate the effectiveness of our model and we achieved 4th place in the DialDoc 2023 Competition. Therefore, CLEM can serve as a solution to resource scarcity in DGDS and provide useful guidance for multi-lingual alignment tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 31 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

26 of 31 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  6. 2018CoQA: A Conversational Question Answering Challengecited by 674
  7. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  8. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  9. 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 124
  10. 2014Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)cited by 109
  11. 2018A Dataset for Document Grounded Conversationscited by 104
  12. 2022Re2G: Retrieve, Rerank, Generatecited by 102
14 more
  1. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  2. 2020CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLPcited by 79
  3. 2018Interpretation of Natural Language Rules in Conversational Machine Readingcited by 72
  4. 2018Towards Exploiting Background Knowledge for Building Conversation Systemscited by 57
  5. 2021MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documentscited by 53
  6. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  7. 2020Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answeringcited by 41
  8. 2019XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answeringcited by 35
  9. 2019Zero-Resource Cross-Lingual Named Entity Recognitioncited by 18
  10. 2021AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NERcited by 17
  11. 2020UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLPcited by 14
  12. 2022ConNER: Consistency Training for Cross-lingual Named Entity Recognitioncited by 11
  13. 2019Cross-Lingual Dependency Parsing Using Code-Mixed TreeBankcited by 10
  14. 2023Coarse-to-Fine Knowledge Selection for Document Grounded Dialogscited by 6

Built on by

Not cited yet.