• Corpus ID: 240420122

Explaining Documents' Relevance to Search Queries

  title={Explaining Documents' Relevance to Search Queries},
  author={Razieh Rahimi and Youngwoo Kim and Hamed Zamani and James Allan},
RAZIEH RAHIMI, Center for Intelligent Information Retrieval, University of Massachusetts Amherst, USA YOUNGWOO KIM, Center for Intelligent Information Retrieval, University of Massachusetts Amherst, USA HAMED ZAMANI, Center for Intelligent Information Retrieval, University of Massachusetts Amherst, USA JAMES ALLAN, Center for Intelligent Information Retrieval, University of Massachusetts Amherst, USA 
2 Citations

Figures and Tables from this paper

Alignment Rationale for Query-Document Relevance
This paper studies how the input perturbations can be used to infer or evaluate alignments between the query and document spans, which best explain the black-box ranker's relevance prediction.
Towards Explainable Search Results: A Listwise Explanation Generator
The proposed LiEGe provides semantic representations at two levels of granularity -- documents and their tokens -- using different interaction signals including cross-document interactions that allow listwise modeling of a search result list as well as the generation of coherent explanations for documents.


Advantages of query biased summaries in information retrieval
Investigation into the utility of document summarisation in the context of information retrieval and the application of so called query biased (or user directed) summaries indicate that the use of query biased summaries significantly improves both the accuracy and speed of user relevance judgements.
Introduction to Information Retrieval
  • R. Larson
  • Computer Science, Environmental Science
    J. Assoc. Inf. Sci. Technol.
  • 2010
This chapter discusses Information Retrieval, the science and technology behind information retrieval and retrieval, and some of the techniques used in the retrieval of information.
Diversifying search results
This work proposes an algorithm that well approximates this objective in general, and is provably optimal for a natural special case, and generalizes several classical IR metrics, including NDCG, MRR, and MAP, to explicitly account for the value of diversification.
Automatically Mining Facets for Queries from Their Search Results
This work proposes a systematic solution, which it refers to as QDMiner, to automatically mine query facets by extracting and grouping frequent lists from free text, HTML tags, and repeat regions within top search results.
EXS: Explainable Search Using Local Model Agnostic Interpretability
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 was this document relevant to the query?''.
LIRME: Locally Interpretable Ranking Model Explanation
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.
Mining subtopics from text fragments for a web query
This paper proposes to use surrounding text of query terms in top retrieved documents to mine subtopics and rank them, and generates a readable subtopic for each cluster based on the cluster and the language model trained from a query log.
Interpreting search result rankings through intent modeling
This paper takes first steps towards a framework for the interpretability of retrieval models with the aim of answering 3 main questions "What is the intent of the query according to the ranker?", "Why is a document ranked higher than another for the query?" and "WhyIs a document relevant to the query?".
Query reformulation using anchor text
It is suggested that anchor text, which is readily available, can be an effective substitute for a query log and the effectiveness of a range of query reformulation techniques (including log-based stemming, substitution, and expansion) using standard TREC collections are studied.
Improving personalized web search using result diversification
Three methods to increase the diversity of the top results are proposed and evaluated and the effectiveness of these methods is evaluated.