Duluth at SemEval-2025 Task 7: TF-IDF with Optimized Vector Dimensions for Multilingual Fact-Checked Claim Retrieval

TL;DR

This paper introduces a TF-IDF-based multilingual claim retrieval system optimized through vector dimensions and tokenization, achieving competitive results but still behind neural methods, highlighting the value of traditional approaches.

Contribution

The paper demonstrates that optimized TF-IDF with specific vector dimensions and tokenization strategies can serve as a strong baseline for multilingual claim retrieval tasks.

Findings

Achieved success@10 score of 0.78 on development set

Best configuration used 15,000 features with word-level tokenization

Traditional TF-IDF methods remain competitive in resource-limited scenarios

Abstract

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.