Neural Information Retrieval: A Literature Review

Abstract

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, this new NN research is often referred to as deep learning. Stemming from this tide of NN work, a number of researchers have recently begun to investigate NN approaches to Information Retrieval (IR). While deep NNs have yet to achieve the same level of success in IR as seen in other areas, the recent surge of interest and work in NNs for IR suggest that this state of affairs may be quickly changing. In this work, we survey the current landscape of Neural IR research, paying special attention to the use of learned representations of queries and documents (i.e., neural embeddings). We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.

arXiv comment44 pages

References in corpus (32)

• Deep Learning in Neural Networks: An Overview
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• LSTM: A Search Space Odyssey
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Natural Language Processing (almost) from Scratch
• Convolutional Neural Networks for Sentence Classification
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• Deep Learning for Answer Sentence Selection
• Text Matching as Image Recognition
• Question Answering with Subgraph Embeddings
• A Dual Embedding Space Model for Document Ranking
• Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews
• Using Word Embeddings for Automatic Query Expansion
• A Study of MatchPyramid Models on Ad-hoc Retrieval
• Multimodal Convolutional Neural Networks for Matching Image and Sentence
• Query Expansion with Locally-Trained Word Embeddings
• Modelling User Preferences using Word Embeddings for Context-Aware Venue Recommendation
• Using Word Embeddings in Twitter Election Classification
• Adaptability of Neural Networks on Varying Granularity IR Tasks
• An empirical study on large scale text classification with skip-gram embeddings
• Representing Documents and Queries as Sets of Word Embedded Vectors for Information Retrieval
• Deep Feature Fusion Network for Answer Quality Prediction in Community Question Answering
• LSTM-Based Predictions for Proactive Information Retrieval
• Learning Dynamic Classes of Events using Stacked Multilayer Perceptron Networks
• Deep Learning Relevance: Creating Relevant Information (as Opposed to Retrieving it)
• Toward Word Embedding for Personalized Information Retrieval
• Selective Term Proximity Scoring Via BP-ANN
• Non-Compositional Term Dependence for Information Retrieval
• Uncertainty in Neural Network Word Embedding: Exploration of Threshold for Similarity

Cited by in corpus (8)

• Medical Deep Learning -- A systematic Meta-Review
• Benchmark for Complex Answer Retrieval
• Data Curation with Deep Learning [Vision]
• Neural Ranking Models with Weak Supervision
• Expeditious Generation of Knowledge Graph Embeddings
• Biomedical Evidence Generation Engine
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact
• Learning to Reformulate the Queries on the WEB