arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.02702cs.IRcs.CL
收藏

用于无监督信息检索的神经向量空间

Neural Vector Spaces for Unsupervised Information Retrieval

University of Amsterdam(阿姆斯特丹大学)

Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas

摘要:

我们提出了神经向量空间模型(NVSM),一种以无监督的方式学习文档表示的方法,用于新闻文章检索。在NVSM范式中,我们从头开始使用梯度下降学习单词和文档的低维表示,并根据它们与由单词表示组成的查询表示的相似性对文档进行排名。我们表明,NVSM表现更好的文档排序比现有的潜在语义向量空间方法。将NVSM添加到词汇语言模型和最先进的基线向量空间模型的混合物中,在检索效率方面产生了统计上显著的增加。因此,NVSM添加了互补的相关性信号。接下来的语义匹配,我们发现NVSM表现良好的情况下,词汇匹配是必要的。NVSM直接从文档集合中学习术语特异性的概念,而无需特征工程。我们还表明,NVSM学习相关的卢恩意义。最后,我们就如何在模型选择(例如,交叉验证)是不可行的。我们发现,使用不同超参数值训练的多个模型的无监督集成比单个交叉验证模型表现得更好。因此,NVSM可以安全地用于对文档进行排名,而无需监督相关性判断。

英文摘要:

We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval. In the NVSM paradigm, we learn low-dimensional representations of words and documents from scratch using gradient descent and rank documents according to their similarity with query representations that are composed from word representations. We show that NVSM performs better at document ranking than existing latent semantic vector space methods. The addition of NVSM to a mixture of lexical language models and a state-of-the-art baseline vector space model yields a statistically significant increase in retrieval effectiveness. Consequently, NVSM adds a complementary relevance signal. Next to semantic matching, we find that NVSM performs well in cases where lexical matching is needed. NVSM learns a notion of term specificity directly from the document collection without feature engineering. We also show that NVSM learns regularities related to Luhn significance. Finally, we give advice on how to deploy NVSM in situations where model selection (e.g., cross-validation) is infeasible. We find that an unsupervised ensemble of multiple models trained with different hyperparameter values performs better than a single cross-validated model. Therefore, NVSM can safely be used for ranking documents without supervised relevance judgments.

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。

↑