mlsanityData to 7 Oct 2026

Cross-Lingual Training with Dense Retrieval for Document Retrieval

arXiv 2109.01628 ↗First posted 3 Sep 2021cs.CL cs.IRcited by 4

Not on the map. Why?

Abstract (arXiv)

Dense retrieval has shown great success in passage ranking in English. However, its effectiveness in document retrieval for non-English languages remains unexplored due to the limitation in training resources. In this work, we explore different transfer techniques for document ranking from English annotations to multiple non-English languages. Our experiments on the test collections in six languages (Chinese, Arabic, French, Hindi, Bengali, Spanish) from diverse language families reveal that zero-shot model-based transfer using mBERT improves the search quality in non-English mono-lingual retrieval. Also, we find that weakly-supervised target language transfer yields competitive performances against the generation-based target language transfer that requires external translators and query generators.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 3 Sep 2021.

Builds on

20 of 32 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  5. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  6. 2019Passage Re-ranking with BERTcited by 629
  7. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  8. 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 266
  9. 2020Pre-training Tasks for Embedding-based Large-scale Retrievalcited by 153
  10. 2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 111
  11. 2019Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrievalcited by 65
  12. 2019Cross-Lingual Natural Language Generation via Pre-Trainingcited by 63
8 more
  1. 2019Simple Applications of BERT for Ad Hoc Document Retrievalcited by 34
  2. 2020Cross-lingual Information Retrieval with BERTcited by 27
  3. 2019Teaching a New Dog Old Tricks: Resurrecting Multilingual Retrieval Using Zero-shot Learningcited by 16
  4. 2021Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrievalcited by 16
  5. 2020A Study of Neural Matching Models for Cross-lingual IRcited by 12
  6. 2019Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representationscited by 11
  7. 2019Cross-Lingual Relevance Transfer for Document Retrievalcited by 9
  8. 2021Cross-language Sentence Selection via Data Augmentation and Rationale Trainingcited by 5

Built on by

Cited by year

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

4 papers.

  1. 2022MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languagescited by 41
  2. 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Modelscited by 36
  3. 2021On Cross-Lingual Retrieval with Multilingual Text Encoderscited by 22
  4. 2022C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrievalcited by 14