# Neural Approaches to Multilingual Information Retrieval

arXiv: https://arxiv.org/abs/2209.01335 · HTML: https://mlsanity.com/paper/2209.01335/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 3 Sep 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models](https://mlsanity.com/paper/2102.00894/) (2021)
- [Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval](https://mlsanity.com/paper/2108.08787/) (2021)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Deeper Text Understanding for IR with Contextual Neural Language Modeling](https://mlsanity.com/paper/1905.09217/) (2019)
- [PLAID: An Efficient Engine for Late Interaction Retrieval](https://mlsanity.com/paper/2205.09707/) (2022)
- [Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval](https://mlsanity.com/paper/2203.05765/) (2022)
- [Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models](https://mlsanity.com/paper/2201.08471/) (2022)
- [BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation](https://mlsanity.com/paper/2109.04588/) (2021)
- [Marian: Cost-effective High-Quality Neural Machine Translation in C++](https://mlsanity.com/paper/1805.12096/) (2018)
- [The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020](https://mlsanity.com/paper/2008.04885/) (2020)
- [Sockeye: A Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1712.05690/) (2017)
- [C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval](https://mlsanity.com/paper/2204.11989/) (2022)
- [Streamlining Evaluation with ir-measures](https://mlsanity.com/paper/2111.13466/) (2021)
- [HC4: A New Suite of Test Collections for Ad Hoc CLIR](https://mlsanity.com/paper/2201.09992/) (2022)
- [Cross-Lingual Relevance Transfer for Document Retrieval](https://mlsanity.com/paper/1911.02989/) (2019)
- [Patapasco: A Python Framework for Cross-Language Information Retrieval Experiments](https://mlsanity.com/paper/2201.09996/) (2022)

## Built on by (most cited first, 18 of 18)

- [Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever](https://mlsanity.com/paper/2408.16672/) (2024)
- [Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness](https://mlsanity.com/paper/2410.01171/) (2024)
- [MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusion](https://mlsanity.com/paper/2503.20698/) (2025)
- [DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search](https://mlsanity.com/paper/2607.27178/) (2026)
- [Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval](https://mlsanity.com/paper/2311.01870/) (2023)
- [IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages](https://mlsanity.com/paper/2312.09508/) (2023)
- [Language Fairness in Multilingual Information Retrieval](https://mlsanity.com/paper/2405.00978/) (2024)
- [PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval](https://mlsanity.com/paper/2405.00975/) (2024)
- [Distillation for Multilingual Information Retrieval](https://mlsanity.com/paper/2405.00977/) (2024)
- [Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methods](https://mlsanity.com/paper/2509.06195/) (2025)
- [V-Agent: An Interactive Video Search System Using Vision-Language Models](https://mlsanity.com/paper/2512.16925/) (2025)
- [CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training](https://mlsanity.com/paper/2604.05821/) (2026)
- [Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval](https://mlsanity.com/paper/2408.10536/) (2024)
- [CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents](https://mlsanity.com/paper/2504.16264/) (2025)
- [HLTCOE at TREC 2023 NeuCLIR Track](https://mlsanity.com/paper/2404.08118/) (2024)
- [Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios](https://mlsanity.com/paper/2509.15380/) (2025)
- [Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research](https://mlsanity.com/paper/2604.17843/) (2026)
- [SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval](https://mlsanity.com/paper/2606.18801/) (2026)

## 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.