用BM25+多语言交叉编码器集成，提升波兰语段落检索效果。
Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders
- 先用BM25粗筛，再用多个现成多语言交叉编码器集成重排。
- 在问答领域性能超越基准，但在法律和客服领域微调后反而下降。
- 适合资源有限、需快速部署的波兰语信息检索场景。
段落检索传统上依赖词法方法如TF-IDF和BM25。近年来，一些神经网络模型虽表现更优，但面临标注数据需求大、难适应新领域等问题。本文提出在Poleval 2023任务3（段落检索）中的胜出方案，目标是从三个领域（趣味知识、法律、客户支持）的波兰语文本中检索相关段落。训练与开发数据仅来自趣味知识领域。方法采用OKAPI BM25进行文档召回，并使用多个公开的多语言交叉编码器组成集成模型进行重排。对重排模型微调虽在训练领域小幅提升性能，但在其他两个领域表现下降。
原文摘要 · Abstract (English)
Passage Retrieval has traditionally relied on lexical methods like TF-IDF and BM25. Recently, some neural network models have surpassed these methods in performance. However, these models face challenges, such as the need for large annotated datasets and adapting to new domains. This paper presents a winning solution to the Poleval 2023 Task 3: Passage Retrieval challenge, which involves retrieving passages of Polish texts in three domains: trivia, legal, and customer support. However, only the trivia domain was used for training and development data. The method used the OKAPI BM25 algorithm to retrieve documents and an ensemble of publicly available multilingual Cross Encoders for Reranking. Fine-tuning the reranker models slightly improved performance but only in the training domain, while it worsened in other domains.
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。