arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.01992cs.CL
收藏

利用交互式和非交互式模型的优势进行基于向量的跨语言信息检索

Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval

Alibaba Group(阿里巴巴集团)

Linlong Xu, Baosong Yang, Xiaoyu Lv, Tianchi Bi, Dayiheng Liu, Haibo Zhang

摘要:

交互式和非交互式模型是基于向量的跨语言信息检索(V-CLIR)的两种事实标准框架,它们分别以同步和异步的方式嵌入查询和文档。从检索精度和计算效率的角度来看,每种模型都有自己的优势和不足。在本文中,我们提出了一个新的框架,以利用这两种范式的优势。具体地说,我们引入半交互式机制,建立我们的模型在非交互式架构,但编码每个文档连同其相关的多语言查询。因此,跨语言特征可以像交互式模型一样被更好地学习。此外,我们进一步转移知识从一个训练有素的互动模型,我们通过重用其词嵌入和采用知识蒸馏。我们的模型从多语言预训练的语言模型M-BERT初始化,并在来自维基百科的两个开放资源CLIR数据集和从现实世界的搜索引擎收集的内部数据集上进行评估。大量的分析表明,我们的方法显着提高检索精度,同时保持计算效率。

英文摘要:

Interactive and non-interactive model are the two de-facto standard frameworks in vector-based cross-lingual information retrieval (V-CLIR), which embed queries and documents in synchronous and asynchronous fashions, respectively. From the retrieval accuracy and computational efficiency perspectives, each model has its own superiority and shortcoming. In this paper, we propose a novel framework to leverage the advantages of these two paradigms. Concretely, we introduce semi-interactive mechanism, which builds our model upon non-interactive architecture but encodes each document together with its associated multilingual queries. Accordingly, cross-lingual features can be better learned like an interactive model. Besides, we further transfer knowledge from a well-trained interactive model to ours by reusing its word embeddings and adopting knowledge distillation. Our model is initialized from a multilingual pre-trained language model M-BERT, and evaluated on two open-resource CLIR datasets derived from Wikipedia and an in-house dataset collected from a real-world search engine. Extensive analyses reveal that our methods significantly boost the retrieval accuracy while maintaining the computational efficiency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑