A Study On The Interpretability Of Neural Retrieval Models Using Deepshap

Abstract

A recent trend in IR has been the usage of neural networks to learn retrieval models for text based adhoc search. While various approaches and architectures have yielded significantly better performance than traditional retrieval models such as BM25, it is still difficult to understand exactly why a document is relevant to a query. In the ML community several approaches for explaining decisions made by deep neural networks have been proposed -- including DeepSHAP which modifies the DeepLift algorithm to estimate the relative importance (shapley values) of input features for a given decision by comparing the activations in the network for a given image against the activations caused by a reference input. In image classification, the reference input tends to be a plain black image. While DeepSHAP has been well studied for image classification tasks, it remains to be seen how we can adapt it to explain the output of Neural Retrieval Models (NRMs). In particular, what is a good "black" ima

Stats

• citations61
• S2 citations—
• github stars0
• HF likes0
• heat score13.44
• arxiv keyfernando2019a

Related papers

• A Deep Look Into Neural Ranking Models For Information Retrieval (2019)17.73
• Towards Axiomatic Explanations For Neural Ranking Models (2021)10.35
• Indicative Image Retrieval: Turning Blackbox Learning Into Grey (2022)0.00
• Neural Models For Information Retrieval (2017)0.00
• Imrnns: An Efficient Method For Interpretable Dense Retrieval Via Embedding Modulation (2026)0.00
• From Distillation To Hard Negative Sampling: Making Sparse Neural IR Models More Effective (2022)0.00
• Incorporating Query Term Independence Assumption For Efficient Retrieval And Ranking Using Deep Neural Networks (2019)0.00
• Neural Information Retrieval: A Literature Review (2016)0.00