Sponsored search systems are tasked with matching queries to relevant advertisements. The current state-of-the-art matching algorithms expand the user’s query using a variety of external resources, such as Web search results. While these expansion-based algorithms are highly effective, they are largely inefficient and cannot be applied in real-time. In practice, such algorithms are applied offline to popular queries, with the results of the expensive operations cached for fast access at query time. In this paper, we describe an efficient and effective approach for matching ads against rare queries that were not processed offline. The approach builds an expanded query representation by leveraging offline processing done for related popular queries. Our experimental results show that our approach significantly improves the effectiveness of advertising on rare queries with only a negligible increase in computational cost.

Query suggestion has been an effective approach to help users narrow down to the information they need. However, most of existing studies focused on only popular/head queries. Since rare queries possess much less information (e.g., clicks) than popular queries in the query logs, it is much more difficult to efficiently suggest relevant queries to a rare query. In this paper, we propose an optimal rare query suggestion framework by leveraging implicit feedbacks from users in the query logs. Our model resembles the principle of pseudo-relevance feedback which assumes that top-returned results by search engines are relevant. However, we argue that the clicked URLs and skipped URLs contain different levels of information and thus should be treated differently. Hence, our framework optimally combines both the click and skip information from users and uses a random walk model to optimize the query correlation. Our model specifically optimizes two parameters: (1) the restarting (jumping) rate of random walk, and (2) the combination ratio of click and skip information. Unlike the Rocchio algorithm, our learning process does not involve the content of the URLs but simply leverages the click and skip counts in the query-URL bipartite graphs. Consequently, our model is capable of scaling up to the need of commercial search engines. Experimental results on one-month query logs from a large commercial search engine with over 40 million rare queries demonstrate the superiority of our framework, with statistical significance, over the traditional random walk models and pseudo-relevance feedback models.

Traditional web search engines treat queries as sequences of keywords and return web pages that contain those keywords as results. Such a mechanism is effective when the user knows exactly the right words that web pages use to describe the content they are looking for. However, it is less than satisfactory or even downright hopeless if the user asks for a concept or topic that has broader and sometimes ambiguous meanings. This is because keyword-based search engines index web pages by keywords and not by concepts or topics. In fact they do not understand the content of the web pages. In this paper, we present a framework that improves web search experiences through the use of a probabilistic knowledge base. The framework classifies web queries into different patterns according to the concepts and entities in addition to keywords contained in these queries. Then it produces answers by interpreting the queries with the help of the knowledge base. Our preliminary results showed that the new framework is capable of answering various types of topic-like queries with much higher user satisfaction, and is therefore a valuable addition to the traditional web search.

Implicit user feedback, including click-through and subsequent browsing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies [1, 2, 3, 13, 25] have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advertisements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site actions in future instances. In particular, we show how post-result behavior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties such as these to predict certain aspects of the user behavior. Additionally, we develop a generative model to mimic trends in observed user activity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a major search engine’s browser toolbar.

In online advertising, pervasive in commercial search engines, advertisers typically bid on few terms, and the scarcity of data makes ad matching difficult. Suggesting additional bidterms can significantly improve ad clickability and conversion rates. In this paper, we present a large-scale bidterm suggestion system that models an advertiser’s intent and finds new bidterms consistent with that intent. Preliminary experiments show that our system significantly increases the coverage of a state of the art production system used at Yahoo while maintaining comparable precision.

Abstract not found

One of the most prevalent online advertising methods is textual advertising. To produce a textual ad, an advertiser must craft a short creative (the text of the ad) linking to a landing page, which describes the product or service being promoted. Furthermore, the advertiser must associate the creative to a set of manually chosen bid phrases representing those Web search queries that should trigger the ad. For efficiency, given a landing page, the bid phrases are often chosen first, and then for each bid phrase the creative is produced using a template. Nevertheless, an ad campaign (e.g., for a large retailer) might involve thousands of landing pages and tens or hundreds of thousands of bid phrases, hence the entire process is very laborious. Our study aims towards the automatic construction of online ad campaigns: given a landing page, we propose several algorithmic methods to generate bid phrases suitable for the given input. Such phrases must be both relevant (that is, reflect the content of the page) and well-formed (that is, likely to be used as queries to a Web search engine). To this end, we use a two phase approach. First, candidate bid phrases are generated by a number of methods, including a (monolingual) translation model capable of generating phrases not contained within the text of the input as well as previously “unseen ” phrases. Second, the candidates are ranked in a probabilistic framework using both the translation model, which favors relevant phrases, as well as a bid phrase language model, which favors well-formed phrases. Empirical evaluation based on a real-life corpus of advertisercreated landing pages and associated bid phrases confirms the value of our approach, which successfully re-generates many of the human-crafted bid phrases and performs significantly better than a pure text extraction method. The research described herein was conducted while the first author was a summer intern at Yahoo! Research.

Unbeknownst to most users, when a query is submitted to a search engine two distinct searches are performed: the organic or algorithmic search that returns relevant Web pages and related data (maps, images, etc.), and the sponsored search that returns paid advertisements. While an enormous amount of work has been invested in understanding the user interaction with organic search, surprisingly little research has been dedicated to what happens after an ad is clicked, a situation we aim to correct. To this end, we define and study the process of context transfer, that is, the user’s transition from Web search to the context of the landing page that follows an ad-click. We conclude that in the vast majority of cases the user is shown one of three types of pages, namely, Homepage (the homepage of the advertiser), Category browse (a browse-able subcatalog related to the original query), and Search transfer (the search results of the same query re-executed on the target site). We show that these three types of landing pages can be accurately distinguished using automatic text classification. Finally, using such an automatic classifier, we correlate the landing page type with conversion data provided by advertisers, and show that the conversion rate (i.e., users ’ response rate to ads) varies considerably according to the type. We believe our findings will further the understanding of users ’ response to search advertising in general, and landing pages in particular, and thus help advertisers improve their Web sites and help search engines select the most suitable ads.

Attributing a dollar value to a keyword is an essential part of running any profitable search engine advertising campaign. When an advertiser has complete control over the interaction with and monetization of each user arriving on a given keyword, the value of that term can be accurately tracked. However, in many instances, the advertiser may monetize arrivals indirectly through one or more third parties. In such cases, it is typical for the third party to provide only coarse-grained reporting: rather than report each monetization event, users are aggregated into larger channels and the third party reports aggregate information such as total daily revenue for each channel. Examples of third parties that use channels include Amazon and Google AdSense. In such scenarios, the number of channels is generally much smaller than the number of keywords whose value per click (VPC) we wish to learn. However, the advertiser has flexibility as to how to assign keywords to channels over time. We introduce the channelization problem: how do we adaptively assign keywords to channels over the course of multiple days to quickly obtain accurate VPC estimates of all keywords? We relate this problem to classical results in weighing design, devise new adaptive algorithms for this problem, and quantify the performance of these algorithms experimentally. Our results demonstrate that adaptive weighing designs that exploit statistics of term

ABSTRACT: User queries and their associated clicks have been extensively explored to improve Web search relevance. Very little existing work explores how user clicks can be used to improve text matching for Web search. In this paper, we treat user queries that result in clicks as off-page annotations. These queries, like anchor text, provide a valuable additional source of relevance information for Web pages. We call the queries that are used to annotate Web pages in this way the QueryText. We propose using the QueryText as a new weighted textual field for Web pages, where the weights are based on user click behavior. We derive two sets of text matching features from the new field – BM25F-based features and n-gram features. We implement the features within a commercial search engine and evaluate the effectiveness of our approach on real large-scale Web data. Our evaluation results show significant improvements in retrieval effectiveness using text match features derived from the QueryText.