Cross-Lingual Relevance Transfer for Document Retrieval
By Peng Shi, Jimmy J. Lin. 2019
16 citations recorded by the source corpus.
Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level relevance modeling for document retrieval to demonstrate the ability of multi-lingual BERT to transfer models of relevance across languages. Experiments on test collections in five different languages from diverse language families (Chinese, Arabic, French, Hindi, and Bengali) show that models trained with English data improve ranking quality, without any special processing, both for (non-English) mono-lingual retrieval as well as cross-lingual retrieval.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jimmy J. Lin
- Sean MacAvaney
- Nazli Goharian
- Luca Soldaini
- Peng Shi
- Richard He Bai
- Zeynep Akkalyoncu Yilmaz
- Rodrigo Nogueira
In Computer Vision and Pattern Recognition
Citations in the corpus
- Cross-Lingual Training of Neural Models for Document Ranking (2020, result): “Note that this is essentially the approach explored in previous work (Shi and Lin, 2019; MacAvaney et al., 2020).”
- Teaching a New Dog Old Tricks: Resurrecting Multilingual Retrieval Using Zero-Shot Learning (2019, methodology): “ligned [19] or unaligned [8] web text, we achieve competitive retrieval performance without having to rely on language specific relevance judgements. During the peer review of this article, a preprint [30] was published with similar observations as ours. In summary, our contributions are: Multilingua”