Neural information retrieval: at the end of the early years

Creative Commons License

Onal K. D. , Zhang Y., ALTINGÖVDE İ. S. , Rahman M. M. , KARAGÖZ P., Braylan A., ...More

INFORMATION RETRIEVAL JOURNAL, vol.21, pp.111-182, 2018 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 21
  • Publication Date: 2018
  • Doi Number: 10.1007/s10791-017-9321-y
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.111-182
  • Keywords: Deep learning, Distributed representation, Neural network, Recurrent neural network, Search engine, Word embedding, Semantic matching, Semantic compositionality, MODELS, NETWORKS, ARCHITECTURES, FREQUENCY


A recent "third wave'' of neural network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, work in this area is often referred to as deep learning. Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created. In this paper, we survey the current landscape of Neural IR research, paying special attention to the use of learned distributed representations of textual units. We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.