# Unsupervised Cross-Lingual Information Retrieval using Monolingual Data Only

arXiv: https://arxiv.org/abs/1805.00879 · HTML: https://mlsanity.com/paper/1805.00879/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2018.

## Built on by (most cited first, 11 of 11)

- [Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation](https://mlsanity.com/paper/2301.12566/) (2023)
- [CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval](https://mlsanity.com/paper/2209.02071/) (2022)
- [Soft Prompt Decoding for Multilingual Dense Retrieval](https://mlsanity.com/paper/2305.09025/) (2023)
- [Mixed Attention Transformer for Leveraging Word-Level Knowledge to Neural Cross-Lingual Information Retrieval](https://mlsanity.com/paper/2109.02789/) (2021)
- [Cross-language Sentence Selection via Data Augmentation and Rationale Training](https://mlsanity.com/paper/2106.02293/) (2021)
- [CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training](https://mlsanity.com/paper/2604.05821/) (2026)
- [Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work](https://mlsanity.com/paper/2503.18471/) (2025)
- [Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval](https://mlsanity.com/paper/2111.01992/) (2021)
- [Cross-language Information Retrieval](https://mlsanity.com/paper/2111.05988/) (2021)
- [Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation](https://mlsanity.com/paper/2401.06583/) (2024)
- [Resource-Lean Lexicon Induction for German Dialects](https://mlsanity.com/paper/2604.23824/) (2026)

## Abstract (arXiv)

We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all. The framework leverages shared cross-lingual word embedding spaces in which terms, queries, and documents can be represented, irrespective of their actual language. The shared embedding spaces are induced solely on the basis of monolingual corpora in two languages through an iterative process based on adversarial neural networks. Our experiments on the standard CLEF CLIR collections for three language pairs of varying degrees of language similarity (English-Dutch/Italian/Finnish) demonstrate the usefulness of the proposed fully unsupervised approach. Our CLIR models with unsupervised cross-lingual embeddings outperform baselines that utilize cross-lingual embeddings induced relying on word-level and document-level alignments. We then demonstrate that further improvements can be achieved by unsupervised ensemble CLIR models. We believe that the proposed framework is the first step towards development of effective CLIR models for language pairs and domains where parallel data are scarce or non-existent.