Papers with mMARCO
Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data (2023.findings-acl)
Copied to clipboard
| Challenge: | Using zero-shot rankers, cross-lingual IR models are limited by their language coverage. |
| Approach: | They propose to train ranking models on artificially code-switched data instead of using a dictionary. |
| Outcome: | The proposed approach is robust towards the ratio of code-switched tokens and extends to unseen languages. |
BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing multilingual evaluation benchmarks focus on IR in the Polish language, but the Polish is a relatively new field due to the limited availability of Polish datasets. |
| Approach: | They propose to establish large-scale resources for IR in the Polish language and translate them into a new benchmark which includes 13 datasets. |
| Outcome: | The proposed benchmarks are based on 13 open IR datasets in Polish and are a pioneering development in this area. |
When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multilingual retrievers are largely untested for mixed language queries . sensitivity of dense retrievers to mixed language querying remains poorly understood . |
| Approach: | They propose to use mixed queries as an interpolation of monolingual embeddings to evaluate retrieval performance. |
| Outcome: | The proposed model outperforms the best monolingual endpoint in 88/105 cases. |