Add to ORKGRecent neural IR models have demonstrated deep learning's utility in ad-hoc information retrieval. However, deep models have a reputation for being black boxes, and the roles of a neural IR model's components may not be obvious at first glance. In this work, we attempt to shed light on the inner workings of a recently proposed neural IR model, namely the PACRR model, by visualizing the output of intermediate layers and by investigating the relationship between intermediate weights and the ultimate relevance score produced. We highlight several insights, hoping that such insights will be generally applicable
Recent developments of machine learning models, and in particular deep neural networks, have yielded...
The advent of deep machine learning platforms such as Tensorflow and Pytorch, developed in expressiv...
The availability of massive data and computing power allowing for effective data driven neural appro...
Recent neural IR models have demonstrated deep learning's utility in ad-hoc information retrieval. H...
Ad-hoc retrieval models can benefit from considering different patterns in the interactions between ...
In order to adopt deep learning for information retrieval, models are needed that can capture all re...
Neural ranking models use shallow or deep neural networks to rank search results in response to a qu...
Machine learning plays a role in many aspects of modern IR systems, and deep learning is applied in ...
A recent "third wave'' of neural network (NN) approaches now delivers state-of-the-art performance i...
Neural networks with deep architectures have demonstrated significant performance improvements in co...
Weak baselines have been present in Information Retrieval (IR) fordecades. They have been associated...
The advent of deep machine learning platforms such as Tensorflow and Pytorch, developed in expressiv...
Recent developments in neural information retrieval models have been promising, but a problem remain...
Deep neural models revolutionized the research landscape in the Information Retrieval (IR) domain. N...
After surpassing human performance in the fields of Computer Vision, Speech Recognition and NLP, dee...
Recent developments of machine learning models, and in particular deep neural networks, have yielded...
The advent of deep machine learning platforms such as Tensorflow and Pytorch, developed in expressiv...
The availability of massive data and computing power allowing for effective data driven neural appro...
Recent neural IR models have demonstrated deep learning's utility in ad-hoc information retrieval. H...
Ad-hoc retrieval models can benefit from considering different patterns in the interactions between ...
In order to adopt deep learning for information retrieval, models are needed that can capture all re...
Neural ranking models use shallow or deep neural networks to rank search results in response to a qu...
Machine learning plays a role in many aspects of modern IR systems, and deep learning is applied in ...
A recent "third wave'' of neural network (NN) approaches now delivers state-of-the-art performance i...
Neural networks with deep architectures have demonstrated significant performance improvements in co...
Weak baselines have been present in Information Retrieval (IR) fordecades. They have been associated...
The advent of deep machine learning platforms such as Tensorflow and Pytorch, developed in expressiv...
Recent developments in neural information retrieval models have been promising, but a problem remain...
Deep neural models revolutionized the research landscape in the Information Retrieval (IR) domain. N...
After surpassing human performance in the fields of Computer Vision, Speech Recognition and NLP, dee...
Recent developments of machine learning models, and in particular deep neural networks, have yielded...
The advent of deep machine learning platforms such as Tensorflow and Pytorch, developed in expressiv...
The availability of massive data and computing power allowing for effective data driven neural appro...