Duluth at SemEval-2025 Task 7: TF-IDF with Optimized Vector Dimensions for Multilingual Fact-Checked Claim Retrieval
This work provides a competitive baseline for multilingual retrieval tasks, particularly useful in scenarios with limited compute resources, but it is incremental as it applies an existing method with optimizations to a new benchmark.
The paper tackled multilingual fact-checked claim retrieval by implementing a TF-IDF-based system with optimized vector dimensions and tokenization, achieving an average success@10 score of 0.69 on the test set across ten languages, though it lagged behind the top system's 0.96.
This paper presents the Duluth approach to the SemEval-2025 Task 7 on Multilingual and Crosslingual Fact-Checked Claim Retrieval. We implemented a TF-IDF-based retrieval system with experimentation on vector dimensions and tokenization strategies. Our best-performing configuration used word-level tokenization with a vocabulary size of 15,000 features, achieving an average success@10 score of 0.78 on the development set and 0.69 on the test set across ten languages. Our system showed stronger performance on higher-resource languages but still lagged significantly behind the top-ranked system, which achieved 0.96 average success@10. Our findings suggest that though advanced neural architectures are increasingly dominant in multilingual retrieval tasks, properly optimized traditional methods like TF-IDF remain competitive baselines, especially in limited compute resource scenarios.