mlsanityData to 7 Oct 2026

Neural Approaches to Multilingual Information Retrieval

arXiv 2209.01335 ↗First posted 3 Sep 2022cs.IR cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

Providing access to information across languages has been a goal of Information Retrieval (IR) for decades. While progress has been made on Cross Language IR (CLIR) where queries are expressed in one language and documents in another, the multilingual (MLIR) task to create a single ranked list of documents across many languages is considerably more challenging. This paper investigates whether advances in neural document translation and pretrained multilingual neural language models enable improvements in the state of the art over earlier MLIR techniques. The results show that although combining neural document translation with neural ranking yields the best Mean Average Precision (MAP), 98% of that MAP score can be achieved with an 84% reduction in indexing time by using a pretrained XLM-R multilingual language model to index documents in their native language, and that 2% difference in effectiveness is not statistically significant. Key to achieving these results for MLIR is to fine-tune XLM-R using mixed-language batches from neural translations of MS MARCO passages.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 21 of its 49 references that are in the map. First posted on arXiv 3 Sep 2022.

Builds on

21 of 49 references.

References · 21

  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. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  6. 2021Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Modelscited by 132
  7. 2021Mr. TyDi: A Multi-lingual Benchmark for Dense Retrievalcited by 118
  8. 2021mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Datasetcited by 116
  9. 2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 111
  10. 2022PLAID: An Efficient Engine for Late Interaction Retrievalcited by 95
  11. 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
  12. 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Modelscited by 36
9 more
  1. 2021BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translationcited by 35
  2. 2018Marian: Cost-effective High-Quality Neural Machine Translation in C++cited by 22
  3. 2020The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020cited by 16
  4. 2017Sockeye: A Toolkit for Neural Machine Translationcited by 15
  5. 2022C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrievalcited by 14
  6. 2021Streamlining Evaluation with ir-measurescited by 10
  7. 2022HC4: A New Suite of Test Collections for Ad Hoc CLIRcited by 10
  8. 2019Cross-Lingual Relevance Transfer for Document Retrievalcited by 9
  9. 2022Patapasco: A Python Framework for Cross-Language Information Retrieval Experimentscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 5; 2026: 4.

18 papers.

Sort:

By area:

  1. 2024Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retrievercited by 25
  2. 2024Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustnesscited by 13
  3. 2025MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusioncited by 8
  4. 2023IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languagescited by 5
  5. 2024Language Fairness in Multilingual Information Retrievalcited by 5
  6. 2023Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrievalcited by 4
  7. 2024PLAID SHIRTTT for Large-Scale Streaming Dense Retrievalcited by 3
  8. 2024Distillation for Multilingual Information Retrievalcited by 3
  9. 2025V-Agent: An Interactive Video Search System Using Vision-Language Modelscited by 3
  10. 2026DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Searchcited by 3
  11. 2025CLIRudit: Cross-Lingual Information Retrieval of Scientific Documentscited by 2
  12. 2025Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methodscited by 2
6 more
  1. 2026CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-trainingcited by 2
  2. 2024HLTCOE at TREC 2023 NeuCLIR Trackcited by 1
  3. 2024Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrievalcited by 1
  4. 2025Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarioscited by 1
  5. 2026Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Researchcited by 1
  6. 2026SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrievalcited by 0