Advertisers use Sponsored Search to drive traffic to their site at a conversion rate and cost per conversion that provides value to them. However, very often advertisers bid at a constant price on a bundle of keywords, either for lack of enough data to fully optimize their bids at a keyword level, or indirectly by opting into Advanced Matching (AM) that allows an advertiser to reach a large number of queries while explicitly bidding only on a limited number. Then this single bid price reflects the return the advertiser gets from the full bundle. Under these conditions, the advertiser is competing too aggressively for some keyword auctions and with too low bids for others. In this paper, we propose a solution to improve the fairness of each keyword's bid prices within an AM bundle: adjusting the AM keyword bid by the ratio of its conversion rate to the conversion rate it would have reached had it been an Exact Match (EM) . First we describe how we measure advertisers' conversion rates despite the opt-in nature of conversion tracking, and illustrate the need for bid adjustment in the context of AM . Then we present our approach to predict conversion rates in a robust manner. Our model uses a number of features capturing the quality of the match between the ad and the query. Then we describe how we adjust keyword bid prices to reflect their value to the advertiser thereby improving (1) the auction through fewer incorrectly high bids in the auction, (2) advertiser return through more auctions won by high value keywords and less by low value keywords, and (3) user satisfaction through higher conversion rate. Finally, we present experimental results from our live system.

Web searchers signal their geographic intent by using place-names in search queries. They also indicate their flexibility about geographic specificity by reformulating their queries. By examining this data we can learn to understand web searcher flexibility with respect to geographic intent. We examine aggregated data of queries with locations, and locations identified from IP addresses, to identify overall distance preferences, as well as distance preferences by search topic. We also examine query rewriting: both deliberate query rewriting, conducted in web search sessions, and automated query rewriting, with manual relevance judgments of geo-modified queries. We find geo-specification in 12.7% of user query rewrites in search sessions, and show the breakdown into sub-classes such as same-city, same-state, same-country and different-country. We also measure the dependence between US-state-name and distance-of-modified-location-from-original-location, finding that Vermont web searchers modify their locations greater distances than California web searchers. We find that automatically-modified queries are perceived as much more relevant when the geographic component is unchanged. We look at the relationship between the non-location part of a query and the distance from the user. We see that people search for child day-care near their locations and maps far from where they are located. We also give distance profiles for the top topics which cooccur with place-names in queries, which could be used to set document priors based on document proximity and query topic.

Sponsored search is a major revenue source for search companies. Web searchers can issue any queries, while advertisement keywords are limited. Query rewriting technique effectively matches user queries with relevant advertisement keywords, thus increases the amount of web advertisements available. The match relevance is critical for clicks. In this study, we aim to improve query rewriting relevance. For this purpose, we use an active learning algorithm called Transductive Experimental Design to select the most informative samples to train the query rewriting relevance model. Experiments show that this approach significantly improves model accuracy and rewriting relevance.

Web searchers signal their geographic intent by using placenames in search queries. They also indicate their flexibility about geographic specificity by reformulating their queries. We conducted experiments on geomodification in query rewriting. We examine both deliberate query rewriting, conducted in user search sessions, and automated query rewriting, with users evaluating the relevance of geo-modified queries. We find geo-specification in 12.7% of user query rewrites in search sessions, and show the breakdown into sub-classes such as same-city, same-state, same-country and different-country. We also measure the dependence between US-state-name and distance-of-modified-location-from-originallocation, finding that Vermont web searchers modify their locations greater distances than California web searchers. We also find that automatically-modified queries are perceived as much more relevant when the geographic component is unchanged.

Web searchers reformulate their queries, as they adapt to search engine behavior, learn more about a topic, or simply correct typing errors. Automatic query rewriting can help user web search, by augmenting a user’s query, or replacing the query with one likely to retrieve better results. One example of query-rewriting is spell-correction. We may also be interested in changing words to synonyms or other related terms. For Japanese, the opportunities for improving results are greater than for languages with a single character set, since documents may be written in multiple character sets, and a user may express the same meaning using different character sets. We give a description of the characteristics of Japanese search query logs and manual query reformulations carried out by Japanese web searchers. We use characteristics of Japanese query reformulations to extend previous work on automatic query rewriting in English, taking into account the Japanese writing system. We introduce several new features for building models resulting from this difference and discuss their impact on automatic query rewriting. We also examine enhancements in the form of rules which block conversion between some character sets, to address Japanese homophones. The precision/recall curves show significant improvement with the new feature set and blocking rules, and are often better than the English counterpart.

We introduce the notion of query substitution, that is, generating a new query to replace a user's original search query. Our technique uses modifications based on typical substitutions web searchers make to their queries. In this way the new query is strongly related to the original query, containing terms closely related to all of the original terms. This contrasts with query expansion through pseudo-relevance feedback, which is costly and can lead to query drift. This also contrasts with query relaxation through boolean or TFIDF retrieval, which reduces the specificity of the query. We define a scale for evaluating query substitution, and show that our method performs well at generating new queries related to the original queries. We build a model for selecting between candidates, by using a number of features relating the query-candidate pair, and by fitting the model to human judgments of relevance of query suggestions. This further improves the quality of the candidates generated. Experiments show that our techniques significantly increase coverage and effectiveness in the setting of sponsored search.