Neural Vector Spaces For Unsupervised Information Retrieval

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 r

Stats

• citations52
• S2 citations—
• github stars0
• HF likes0
• heat score12.93
• arxiv keyvangysel2017neural

Related papers

• Vectorsearch: Enhancing Document Retrieval With Semantic Embeddings And Optimized Search (2024)0.00
• Semantic Vector Encoding And Similarity Search Using Fulltext Search Engines (2017)6.77
• Evaluating The Impact Of Word Embeddings On Similarity Scoring In Practical Information Retrieval (2026)0.00
• Gleanvec: Accelerating Vector Search With Minimalist Nonlinear Dimensionality Reduction (2024)0.00
• Ultra-high Dimensional Sparse Representations With Binarization For Efficient Text Retrieval (2021)8.60
• Beyond Precision: A Study On Recall Of Initial Retrieval With Neural Representations (2018)4.52
• Neural Models For Information Retrieval (2017)0.00
• Vector Embedding Of Multi-modal Texts: A Tool For Discovery? (2025)0.00