CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval
This addresses the challenge of fact-checking in low-resource languages where data is scarce, though it is incremental as it builds on existing cross-lingual transfer techniques.
The paper tackles the problem of cross-lingual fact-checking by introducing a framework that uses cross-lingual retrieval to aggregate evidence from multiple languages, achieving a 2.23% absolute F1 improvement in zero-shot cross-lingual setup on the X-Fact dataset.
Fact-checking has gained increasing attention due to the widespread of falsified information. Most fact-checking approaches focus on claims made in English only due to the data scarcity issue in other languages. The lack of fact-checking datasets in low-resource languages calls for an effective cross-lingual transfer technique for fact-checking. Additionally, trustworthy information in different languages can be complementary and helpful in verifying facts. To this end, we present the first fact-checking framework augmented with cross-lingual retrieval that aggregates evidence retrieved from multiple languages through a cross-lingual retriever. Given the absence of cross-lingual information retrieval datasets with claim-like queries, we train the retriever with our proposed Cross-lingual Inverse Cloze Task (X-ICT), a self-supervised algorithm that creates training instances by translating the title of a passage. The goal for X-ICT is to learn cross-lingual retrieval in which the model learns to identify the passage corresponding to a given translated title. On the X-Fact dataset, our approach achieves 2.23% absolute F1 improvement in the zero-shot cross-lingual setup over prior systems. The source code and data are publicly available at https://github.com/khuangaf/CONCRETE.