National Institute of Standards and Technology における超伝導研究及び生活

This tutorial is concerned with a comprehensive introduction to the research area of learning to rank for information retrieval. In the first part of the tutorial, we will introduce three major approaches to learning to rank, i.e., the pointwise, pairwise, and listwise approaches, analyze the relationship between the loss functions used in these approaches and the widely-used IR evaluation measures, evaluate the performance of these approaches on the LETOR benchmark datasets, and demonstrate how to use these approaches to solve real ranking applications. In the second part of the tutorial, we will discuss some advanced topics regarding learning to rank, such as relational ranking, diverse ranking, semi-supervised ranking, transfer ranking, query-dependent ranking, and training data preprocessing. In the third part, we will briefly mention the recent advances on statistical learning theory for ranking, which explain the generalization ability and statistical consistency of different ranking methods. In the last part, we will conclude the tutorial and show several future research directions.

/pdf/learning-to-rank-for-information-retrieval-2q6t3viyug.pdf

Learning to Rank for Information Retrieval

Classic IR (information retrieval) is inherently predicated on users searching for information, the so-called "information need". But the need behind a web search is often not informational -- it might be navigational (give me the url of the site I want to reach) or transactional (show me sites where I can perform a certain transaction, e.g. shop, download a file, or find a map). We explore this taxonomy of web searches and discuss how global search engines evolved to deal with web-specific needs.

/pdf/a-taxonomy-of-web-search-1c1wfauugs.pdf

A taxonomy of web search

This paper addresses several key issues in the ArnetMiner system, which aims at extracting and mining academic social networks. Specifically, the system focuses on: 1) Extracting researcher profiles automatically from the Web; 2) Integrating the publication data into the network from existing digital libraries; 3) Modeling the entire academic network; and 4) Providing search services for the academic network. So far, 448,470 researcher profiles have been extracted using a unified tagging approach. We integrate publications from online Web databases and propose a probabilistic framework to deal with the name ambiguity problem. Furthermore, we propose a unified modeling approach to simultaneously model topical aspects of papers, authors, and publication venues. Search services such as expertise search and people association search have been provided based on the modeling results. In this paper, we describe the architecture and main features of the system. We also present the empirical evaluation of the proposed methods.

ArnetMiner: extraction and mining of academic social networks

The Probabilistic Relevance Framework (PRF) is a formal framework for document retrieval, grounded in work done in the 1970—1980s, which led to the development of one of the most successful text-retrieval algorithms, BM25. In recent years, research in the PRF has yielded new retrieval models capable of taking into account document meta-data (especially structure and link-graph information). Again, this has led to one of the most successful Web-search and corporate-search algorithms, BM25F. This work presents the PRF from a conceptual point of view, describing the probabilistic modelling assumptions behind the framework and the different ranking algorithms that result from its application: the binary independence model, relevance feedback models, BM25 and BM25F. It also discusses the relation between the PRF and other statistical models for IR, and covers some related topics, such as the use of non-textual features, and parameter optimisation for models with free parameters.

/pdf/the-probabilistic-relevance-framework-290mics7xy.pdf

The Probabilistic Relevance Framework

Search engine click logs provide an invaluable source of relevance information, but this information is biased. A key source of bias is presentation order: the probability of click is influenced by a document's position in the results page. This paper focuses on explaining that bias, modelling how probability of click depends on position. We propose four simple hypotheses about how position bias might arise. We carry out a large data-gathering effort, where we perturb the ranking of a major search engine, to see how clicks are affected. We then explore which of the four hypotheses best explains the real-world position effects, and compare these to a simple logistic regression model. The data are not well explained by simple position models, where some users click indiscriminately on rank 1 or there is a simple decay of attention over ranks. A 'cascade' model, where users view results from top to bottom and leave as soon as they see a worthwhile document, is our best explanation for position bias in early ranks

An experimental comparison of click position-bias models

We introduce a large scale MAchine Reading COmprehension dataset, which we name MS MARCO. The dataset comprises of 1,010,916 anonymized questions---sampled from Bing's search query logs---each with a human generated answer and 182,669 completely human rewritten generated answers. In addition, the dataset contains 8,841,823 passages---extracted from 3,563,535 web documents retrieved by Bing---that provide the information necessary for curating the natural language answers. A question in the MS MARCO dataset may have multiple answers or no answers at all. Using this dataset, we propose three different tasks with varying levels of difficulty: (i) predict if a question is answerable given a set of context passages, and extract and synthesize the answer as a human would (ii) generate a well-formed answer (if possible) based on the context passages that can be understood with the question and passage context, and finally (iii) rank a set of retrieved passages given a question. The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering. We believe that the scale and the real-world nature of this dataset makes it attractive for benchmarking machine reading comprehension and question-answering models.

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Search engines can record which documents were clicked for which query, and use these query-document pairs as "soft" relevance judgments. However, compared to the true judgments, click logs give noisy and sparse relevance information. We apply a Markov random walk model to a large click log, producing a probabilistic ranking of documents for a given query. A key advantage of the model is its ability to retrieve relevant documents that have not yet been clicked for that query and rank those effectively. We conduct experiments on click logs from image search, comparing our ("backward") random walk model to a different ("forward") random walk, varying parameters such as walk length and self-transition probability. The most effective combination is a long backward walk with high self-transition probability.

https://www.microsoft.com/en-us/research/wp-content/uploads/2007/07/craswellszummer-random-walks-sigir07.pdf

Random walks on the click graph

Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space. In traditional information retrieval models, on the other hand, terms have discrete or local representations, and the relevance of a document is determined by the exact matches of query terms in the body text. We hypothesize that matching with distributed representations complements matching with traditional local representations, and that a combination of the two is favourable. We propose a novel document ranking model composed of two separate deep neural networks, one that matches the query and the document using a local representation, and another that matches the query and the document using learned distributed representations. The two networks are jointly trained as part of a single neural network. We show that this combination or 'duet' performs significantly better than either neural network individually on a Web page ranking task, and significantly outperforms traditional baselines and other recently proposed models based on neural networks.

/pdf/learning-to-match-using-local-and-distributed-1hem3dwkqw.pdf

Learning to Match using Local and Distributed Representations of Text for Web Search

The goal of the enterprise track is to conduct experiments with enterprise data — intranet pages, email archives, document repositories — that reflect the experiences of users in real organisations, such that for example, an email ranking technique that is effective here would be a good choice for deployment in a real multi-user email search application. This involves both understanding user needs in enterprise search and development of appropriate IR techniques.

/pdf/overview-of-the-trec-2005-enterprise-track-30742guupe.pdf

Nick Craswell

Papers

An experimental comparison of click position-bias models

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Random walks on the click graph

Learning to Match using Local and Distributed Representations of Text for Web Search

Overview of the TREC-2005 Enterprise Track