优化TF-IDF向量维度，实现多语言事实核查语句检索的高效基线。
Duluth at SemEval-2025 Task 7: TF-IDF with Optimized Vector Dimensions for Multilingual Fact-Checked Claim Retrieval
- 基于TF-IDF与词级分词，通过调优向量维度提升检索效果。
- 在10种语言上平均success@10达0.78（开发集）和0.69（测试集）。
- 适合资源受限场景，为复杂模型提供可比性基准。
本文介绍Duluth团队在SemEval-2025任务7——多语言与跨语言事实核查语句检索中的方法。我们构建了一个基于TF-IDF的检索系统，实验了不同向量维度与分词策略。最佳配置采用词级分词，词汇表大小为15,000特征，在十种语言上的开发集平均success@10得分为0.78，测试集为0.69。系统在高资源语言上表现较好，但仍显著落后于排名第一的系统（0.96平均success@10）。结果表明，尽管先进神经架构在多语言检索中日益主导，但经合理优化的传统方法如TF-IDF，仍可在计算资源有限的情况下作为有力基准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。