Neural ranking models for document retrieval
arXiv:2102.11903 · doi:10.1007/s10791-021-09398-0
Abstract
Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep learning models in information retrieval. These models are trained end-to-end to extract features from the raw data for ranking tasks, so that they overcome the limitations of hand-crafted features. A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking. In this paper, we compare the proposed models in the literature along different dimensions in order to understand the major contributions and limitations of each model. In our discussion of the literature, we analyze the promising neural components, and propose future research directions. We also show the analogy between document retrieval and other retrieval tasks where the items to be ranked are structured documents, answers, images and videos.
arXiv commentPublished in the Information Retrieval Journal (2021)
References in corpus (50)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Efficient Estimation of Word Representations in Vector Space
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distributed Representations of Words and Phrases and their Compositionality
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Semi-Supervised Classification with Graph Convolutional Networks
- Natural Language Processing (almost) from Scratch
- Distributed Representations of Sentences and Documents
- On the difficulty of training Recurrent Neural Networks
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Graph Neural Networks: A Review of Methods and Applications
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- Character-Aware Neural Language Models
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- Reasoning about Entailment with Neural Attention
- Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval
- End-to-End Neural Ad-hoc Ranking with Kernel Pooling
- Semi-supervised Sequence Learning
- Deeper Text Understanding for IR with Contextual Neural Language Modeling
- Reformer: The Efficient Transformer
- Query expansion techniques for information retrieval: A survey
- CEDR: Contextualized Embeddings for Document Ranking
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
- DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval
- Human Activity Recognition using Recurrent Neural Networks
- A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
- Learning a Text-Video Embedding from Incomplete and Heterogeneous Data
- Recent Advance in Content-based Image Retrieval: A Literature Survey
- A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
- Understanding the Behaviors of BERT in Ranking
- Simple Applications of BERT for Ad Hoc Document Retrieval
- Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
- Ad Hoc Table Retrieval using Semantic Similarity
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- Word-Entity Duet Representations for Document Ranking
- Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
- Pretrained Transformers for Text Ranking: BERT and Beyond
- A Study of MatchPyramid Models on Ad-hoc Retrieval
- Product Knowledge Graph Embedding for E-commerce
- Learning Deep Representations of Medical Images using Siamese CNNs with Application to Content-Based Image Retrieval
- A Compare-Aggregate Model for Matching Text Sequences
- Table Search Using a Deep Contextualized Language Model
- Match-Tensor: a Deep Relevance Model for Search
- DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval
- Semantic Labeling Using a Deep Contextualized Language Model