Neural Vector Spaces for Unsupervised Information Retrieval

TL;DR

The paper introduces NVSM, an unsupervised neural vector space model for news article retrieval that improves document ranking by learning semantic representations directly from data, enhancing effectiveness over existing methods.

Contribution

The paper presents NVSM, a novel unsupervised neural approach for learning document and word representations for information retrieval, outperforming existing latent semantic models.

Findings

NVSM outperforms existing latent semantic vector space methods.

Adding NVSM improves retrieval effectiveness when combined with lexical models.

NVSM effectively captures term specificity and relevance signals without supervision.

Abstract

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.