Neural information retrieval: at the end of the early years

@article{Onal2017NeuralIR,
  title={Neural information retrieval: at the end of the early years},
  author={Kezban Dilek Onal and Ye Zhang and Ismail Seng{\"o}r Alting{\"o}vde and Md. Mustafizur Rahman and Pinar Senkul and Alexander Braylan and Brandon Dang and Heng-Lu Chang and Henna Kim and Quinten McNamara and Aaron Angert and Edward Banner and Vivek Khetan and Tyler McDonnell and An Thanh Nguyen and Dan Xu and Byron C. Wallace and M. de Rijke and Matthew Lease},
  journal={Information Retrieval Journal},
  year={2017},
  volume={21},
  pages={111 - 182},
  url={https://api.semanticscholar.org/CorpusID:21684923}
}
The successes of neural IR thus far are highlighted, obstacles to its wider adoption are cataloged, and potentially promising directions for future research are suggested.
View on Springer Nature
link.springer.com
136 Citations
Highly Influential Citations
1
Background Citations
54
Methods Citations
19

136 Citations

Neural information retrieval: introduction to the special issue

This special issue of the Information Retrieval journal provides an additional venue for the findings from research happening at the intersection of information retrieval and neural networks.

SIGIR 2017 Workshop on Neural Information Retrieval (Neu-IR'17)

The workshop will request the community to submit proposals on generating large scale benchmark collections, building a shared model repository, and standardizing frameworks appropriate for evaluating deep neural network models.

Continual Learning of Long Topic Sequences in Neural Information Retrieval - abstract

This paper proposes a dataset based upon the MSMarco corpus aiming at modeling a long stream of topics as well as IR property-driven controlled settings and in-depth analyzes the ability of recent neural IR models while continually learning those streams.

Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges

A survey that focuses on a comprehensive analysis of prevalent approaches that apply pretrained transformer encoders like BERT to IR and highlights the advantages of employing encoder-based BERT models in contrast to recent large language models like ChatGPT, which are decoder-based and demand extensive computational resources.

A Survey of Model Architectures in Information Retrieval

This work surveys the evolution of model architectures in IR, focusing on two key aspects: backbone models for feature extraction and end-to-end system architectures for relevance estimation, tracing the development from traditional term-based methods to modern neural approaches.

A Deep Look into Neural Ranking Models for Information Retrieval

An Introduction to Neural Information Retrieval

The monograph provides a complete picture of neural information retrieval techniques that culminate in supervised neural learning to rank models including deep neural network architectures that are trained end-to-end for ranking tasks.

Focal elements of neural information retrieval models. An outlook through a reproducibility study

Neural methods for effective, efficient, and exposure-aware information retrieval

This thesis presents novel neural architectures and methods motivated by the specific needs and challenges of IR tasks, and develops a framework to incorporate query term independence into any arbitrary deep model that enables large-scale precomputation and the use of inverted index for fast retrieval.

Explainability of Text Processing and Retrieval Methods: A Critical Survey

Approaches that have been applied to explain word embeddings, sequence modeling, attention modules, transformers, BERT are surveyed.
...

228 References

Deep Learning for Information Retrieval

This tutorial aims at summarizing and introducing the results of recent research on deep learning for information retrieval, in order to stimulate and foster more significant research and development work on the topic in the future.

Adaptability of Neural Networks on Varying Granularity IR Tasks

The role of the granularity on the performance of common state of the art DNN structures in IR is examined to help clarify the role of granularity in the training and performance of DNNs on IR tasks.

Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks

This paper presents a convolutional neural network architecture for reranking pairs of short texts, where the optimal representation of text pairs and a similarity function to relate them in a supervised way from the available training data are learned.

Very Deep Convolutional Networks for Natural Language Processing

This work presents a new architecture for text processing which operates directly on the character level and uses only small convolutions and pooling operations, and is able to show that the performance of this model increases with the depth.

A Primer on Neural Network Models for Natural Language Processing

This tutorial surveys neural network models from the perspective of natural language processing research, in an attempt to bring natural-language researchers up to speed with the neural techniques.

Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval

This work develops a multi-task DNN for learning representations across multiple tasks, not only leveraging large amounts of cross-task data, but also benefiting from a regularization effect that leads to more general representations to help tasks in new domains.

Learning semantic representations using convolutional neural networks for web search

This paper presents a series of new latent semantic models based on a convolutional neural network to learn low-dimensional semantic vectors for search queries and Web documents that significantly outperforms other se-mantic models in retrieval performance.

Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding

The results show that on this task, both types of recurrent networks outperform the CRF baseline substantially, and a bi-directional Jordantype network that takes into account both past and future dependencies among slots works best, outperforming a CRFbased baseline by 14% in relative error reduction.

Natural Language Processing (Almost) from Scratch

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity…

LSTM: A Search Space Odyssey

This paper presents the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling, and observes that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
...