We present a deep learning based room image retrieval framework that is based on style understanding. Given a dataset of room images labeled by interior design experts, we map the noisy style labels to comparison labels. Our framework learns the style spectrum of each image from the generated comparisons and makes significantly more accurate recommendations compared to discrete classification baselines.

Recent work introduced a probabilistic framework that measures search engine performance information-theoretically. This allows for novel meta-evaluation measures such as Information Difference, which measures the magnitude of the difference between search engines in their ranking of documents. for which we have relevance information. Using Information Difference we can compare the behavior of search engines-which documents the search engine prefers, as well as search engine performance-how likely the search engine is to satisfy a hypothetical user. In this work, we a) extend this probabilistic framework to precision-oriented contexts, b) show that Information Difference can be used to detect similar search engines at shallow ranks, and c) demonstrate the utility of the Information Difference methodology by showing that well-tuned search engines employing different retrieval models are more similar than a well-tuned and a poorly tuned implementation of the same retrieval model.

Document-level relevance judgments are a major component in the calculation of effectiveness metrics. Collecting high-quality judgments is therefore a critical step in information retrieval evaluation. However, the nature of and the assumptions underlying relevance judgment collection have not received much attention. In particular, relevance judgments are typically collected for each document in isolation, although users read each document in the context of other documents. In this work, we aim to investigate the nature of relevance judgment collection. We collect relevance labels in both isolated and conditional setting, and ask for judgments in various dimensions of relevance as well as overall relevance. Then we compare the relevance metrics based on various types of judgments with other metrics of quality such as user preference. Our analyses illuminate how these settings for judgment collection affect the quality and the characteristics of the judgments. We also find that the metrics based on conditional judgments show higher correlation with user preference than isolated judgments.

High quality relevance judgments are essential for the evaluation of information retrieval systems. Traditional methods of collecting relevance judgments are based on collecting binary or graded nominal judgments, but such judgments are limited by factors such as inter-assessor disagreement and the arbitrariness of grades. Previous research has shown that it is easier for assessors to make pairwise preference judgments. However, unless the preferences collected are largely transitive, it is not clear how to combine them in order to obtain document relevance scores. Another difficulty is that the number of pairs that need to be assessed is quadratic in the number of documents. In this work, we consider the problem of inferring document relevance scores from pairwise preference judgments by analogy to tournaments using the Elo rating system. We show how to combine a linear number of pairwise preference judgments from multiple assessors to compute relevance scores for every document.

We consider the problem of information retrieval evaluation and the methods and metrics used for such evaluations. We propose a probabilistic framework for evaluation which we use to develop new information-theoretic evaluation metrics. We demonstrate that these new metrics are powerful and generalizable, enabling evaluations heretofore not possible.

The development of information retrieval systems such as search engines relies on good test collections, including assessments of retrieved content. The widely employed Cranfield paradigm dictates that the information relevant to a topic be encoded at the level of documents, therefore requiring effectively complete document relevance assessments. As this is no longer practical for modern corpora, numerous problems arise, including scalability, reusability, and applicability. We propose a new method for relevance assessment based on relevant information, not relevant documents. Once the relevant 'nuggets' are collected, our matching method can assess any document for relevance with high accuracy, and so any retrieved list of documents can be assessed for performance. In this paper we analyze the performance of the matching function by looking at specific cases and by comparing with other methods. We then show how these inferred relevance assessments can be used to perform IR system evaluation, and we discuss in particular reusability and scalability. Our main contribution is a methodology for producing test collections that are highly accurate, more complete, scalable, reusable, and can be generated with similar amounts of effort as existing methods, with great potential for future applications.

The problem of building test collections is central to the development of information retrieval systems such as search engines. Starting with a few relevant "nuggets" of information manually extracted from existing TREC corpora, we implement and test a methodology that finds and correctly assesses the vast majority of relevant documents found by TREC assessors - as well as up to four times more additional relevant documents. Our methodology produces highly accurate test collections that hold the promise of addressing the issues of scalability, reusability, and applicability.