Proceedings Article10.1145/3289600.3290620
EXS: Explainable Search Using Local Model Agnostic Interpretability
Jaspreet Singh,Avishek Anand +1 more
- 30 Jan 2019
- pp 770-773
TL;DR: ExS as discussed by the authors is a search system designed specifically to provide its users with insight into the following questions: "What is the intent of the query according to the ranker?"", "Why is this document ranked higher than another?'' and "This document relevant to the query?"
read more
Abstract: Retrieval models in information retrieval are used to rank documents for typically under-specified queries. Today machine learning is used to learn retrieval models from click logs and/or relevance judgments that maximizes an objective correlated with user satisfaction. As these models become increasingly powerful and sophisticated, they also become harder to understand. Consequently, it is hard for to identify artifacts in training, data specific biases and intents from a complex trained model like neural rankers even if trained purely on text features. EXS is a search system designed specifically to provide its users with insight into the following questions: "What is the intent of the query according to the ranker?'', "Why is this document ranked higher than another?'' and "Why is this document relevant to the query?''. EXS uses a version of a popular posthoc explanation method for classifiers -- LIME, adapted specifically to answer these questions. We show how such a system can effectively help a user understand the results of neural rankers and highlight areas of improvement.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
BERTology Meets Biology: Interpreting Attention in Protein Language Models
TL;DR: This article analyzed the inner workings of the Transformer and explore how the model discerns structural and functional properties of proteins, showing that attention captures the folding structure of proteins and targets binding sites, a key functional component of proteins.
Meaningful Explanations of Black Box AI Decision Systems.
Dino Pedreschi,Fosca Giannotti,Riccardo Guidotti,Anna Monreale,Salvatore Ruggieri,Franco Turini +5 more
- 17 Jul 2019
TL;DR: This work focuses on the urgent open challenge of how to construct meaningful explanations of opaque AI/ML systems, introducing the local-toglobal framework for black box explanation, articulated along three lines: the language for expressing explanations in terms of logic rules, statistical and causal interpretation, and the inference of local explanations for revealing the decision rationale for a specific case.
Explainable Recommendation: A Survey and New Perspectives
Yongfeng Zhang,Xu Chen +1 more
TL;DR: Explainable recommendation as discussed by the authors attempts to develop models that generate not only high-quality recommendations but also intuitive explanations, where the explanations may either come from an explainable model (also called interpretable or transparent model in some contexts).
142
Injury severity on traffic crashes: A text mining with an interpretable machine-learning approach
TL;DR: This study combines machine learning-based text mining with GCV-LIME to identify likely causality factors for injury severities while providing interpretability as required by traffic safety analysts to identify factors associated with high injury-severity levels.
81
LIRME: Locally Interpretable Ranking Model Explanation
Manisha Verma,Debasis Ganguly +1 more
- 18 Jul 2019
TL;DR: This work explores three sampling methods to train an explanation model and proposes two metrics to evaluate explanations generated for an IR model, revealing that diversity in samples is important for training local explanation models, and the stability of a model is inversely proportional to the number of parameters used to explain the model.
77
References
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro,Sameer Singh,Carlos Guestrin +2 more
- 13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
•Proceedings Article
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu,Jimmy Ba,Ryan Kiros,Kyunghyun Cho,Aaron Courville,Ruslan Salakhudinov,Ruslan Salakhudinov,Rich Zemel,Rich Zemel,Yoshua Bengio,Yoshua Bengio +10 more
- 06 Jul 2015
TL;DR: An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound.
•Posted Content
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu,Jimmy Ba,Ryan Kiros,Kyunghyun Cho,Aaron Courville,Ruslan Salakhutdinov,Richard S. Zemel,Yoshua Bengio +7 more
TL;DR: This paper proposed an attention-based model that automatically learns to describe the content of images by focusing on salient objects while generating corresponding words in the output sequence, which achieved state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.
5.9K
•Posted Content
Towards A Rigorous Science of Interpretable Machine Learning
Finale Doshi-Velez,Been Kim +1 more
TL;DR: This position paper defines interpretability and describes when interpretability is needed (and when it is not), and suggests a taxonomy for rigorous evaluation and exposes open questions towards a more rigorous science of interpretable machine learning.
4K
•Proceedings Article
Anchors: High-Precision Model-Agnostic Explanations
Marco Tulio Ribeiro,Sameer Singh,Carlos Guestrin +2 more
- 25 Apr 2018
TL;DR: This work introduces a novel model-agnostic system that explains the behavior of complex models with high-precision rules called anchors, representing local, “sufficient” conditions for predictions, and proposes an algorithm to efficiently compute these explanations for any black-box model with high probability guarantees.
2.2K
Related Papers (5)
Scott M. Lundberg,Su-In Lee +1 more
- 04 Dec 2017
Stephen Robertson,Hugo Zaragoza +1 more
- 17 Dec 2009