Large language models (LLMs) are increasingly integral to information retrieval (IR), powering ranking, evaluation, and AI-assisted content creation. This widespread adoption necessitates a critical examination of potential biases arising from the interplay between these LLM-based components. This paper synthesizes existing research and presents novel experiment designs that explore how LLM-based rankers and assistants influence LLM-based judges. We provide the first empirical evidence of LLM judges exhibiting significant bias towards LLM-based rankers. Furthermore, we observe limitations in LLM judges' ability to discern subtle system performance differences. Contrary to some previous findings, our preliminary study does not find evidence of bias against AI-generated content. These results highlight the need for a more holistic view of the LLM-driven information ecosystem. To this end, we offer initial guidelines and a research agenda to ensure the reliable use of LLMs in IR evaluation.

Generative information retrieval (Gen-IR) is a fast-growing interdisciplinary research area that investigates how to leverage advances in generative Artificial Intelligence (AI) to improve information retrieval systems. Gen-IR has attracted interest from the information retrieval, natural language processing, and machine learning communities, among others. Since the dawn of Gen-IR last year, there has been an explosion of Gen-IR systems that have launched and are now widely used. Interest in this area across academia and industry is only expected to continue to grow as new research challenges and application opportunities arise. The goal of this proposed workshop, The Second Workshop on Generative Information Retrieval (Gen-IR @ SIGIR 2024) is to provide an interactive venue for exploring a broad range of foundational and applied Gen-IR research. The workshop will focus on tasks such as generative document retrieval, grounded answer generation, generative recommendation, and generative knowledge graphs, all through the lens of model training, model behavior, and broader issues. The workshop will be highly interactive, favoring panel discussions, poster sessions, and roundtable discussions over one-sided keynotes and paper talks.

Work in information retrieval has largely been centered around ranking and relevance: given a query, return some number of results ordered by relevance to the user. The problem of result list truncation, or where to truncate the ranked list of results, however, has received less attention despite being crucial in a variety of applications. Such truncation is a balancing act between the overall relevance, or usefulness of the results, with the user cost of processing more results. Result list truncation can be challenging because relevance scores are often not well-calibrated. This is particularly true in large-scale IR systems where documents and queries are embedded in the same metric space and a query's nearest document neighbors are returned during inference. Here, relevance is inversely proportional to the distance between the query and candidate document, but what distance constitutes relevance varies from query to query and changes dynamically as more documents are added to the index. In this work, we propose Surprise scoring, a statistical method that leverages the Generalized Pareto Distribution that arises in extreme value theory to produce interpretable and calibrated relevance scores at query time using nothing more than the ranked scores. We demonstrate its effectiveness on the result list truncation task across image, text, and IR datasets and compare it to both classical and recent baselines. We draw connections to hypothesis testing and p-values.

Generative information retrieval (IR) has experienced substantial growth across multiple research communities (e.g., information retrieval, computer vision, natural language processing, and machine learning), and has been highly visible in the popular press. Theoretical, empirical, and actual user-facing products have been released that retrieve documents (via generation) or directly generate answers given an input request. We would like to investigate whether end-to-end generative models are just another trend or, as some claim, a paradigm change for IR. This necessitates new metrics, theoretical grounding, evaluation methods, task definitions, models, user interfaces, etc. The goal of this workshop1 is to focus on previously explored Generative IR techniques like document retrieval and direct Grounded Answer Generation, while also offering a venue for the discussion and exploration of how Generative IR can be applied to new domains like recommendation systems, summarization, etc. The format of the workshop is interactive, including roundtable and keynote sessions and tends to avoid the one-sided dialogue of a mini-conference.

On the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages. As such, building highly effective classifiers that enable a safer internet is an important research area. Moreover, the web is a highly multilingual, cross-cultural community that develops its own lingo over time. As such, it is crucial to develop models that are effective across a diverse range of languages, usages, and styles. In this paper, we present the fundamentals behind the next version of the Perspective API from Google Jigsaw. At the heart of the approach is a single multilingual token-free Charformer model that is applicable across a range of languages, domains, and tasks. We demonstrate that by forgoing static vocabularies, we gain flexibility across a variety of settings. We additionally outline the techniques employed to make such a byte-level model efficient and feasible for productionization. Through extensive experiments on multilingual toxic comment classification benchmarks derived from real API traffic and evaluation on an array of code-switching, covert toxicity, emoji-based hate, human-readable obfuscation, distribution shift, and bias evaluation settings, we show that our proposed approach outperforms strong baselines. Finally, we present our findings from deploying this system in production.

Although information access systems have long supportedpeople in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models. In this way, the core principles of indexing, representation, retrieval, and ranking can be applied and extended to substantially improve model generalization, scalability, robustness, and interpretability. We describe a generic retrieval-enhanced machine learning (REML) framework, which includes a number of existing models as special cases. REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization. The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.

Email has been an essential communication medium for many years. As a result, the information accumulated in our mailboxes has become valuable for all of our personal and professional activities. For years, researchers have developed interfaces, models, and algorithms to facilitate email search, discovery, and organization. This tutorial brings together these diverse research directions and provides both a historical background, as well as a high-level overview of the recent advances in the field. In particular, we lay out all of the components needed in the design of email search engines, including user interfaces, indexing, document and query understanding, retrieval, ranking, evaluation, and data privacy. The tutorial also goes beyond search, presenting recent work on intelligent task assistance in email and a number of interesting future directions.

Large generative language models such as GPT-2 are well-known for their ability to generate text as well as their utility in supervised downstream tasks via fine-tuning. Its prevalence on the web, however, is still not well understood - if we run GPT-2 detectors across the web, what will we find? Our work is twofold: firstly we demonstrate via human evaluation that classifiers trained to discriminate between human and machine-generated text emerge as unsupervised predictors of "page quality", able to detect low quality content without any training. This enables fast bootstrapping of quality indicators in a low-resource setting. Secondly, curious to understand the prevalence and nature of low quality pages in the wild, we conduct extensive qualitative and quantitative analysis over 500 million web articles, making this the largest-scale study ever conducted on the topic.

Quick Access is a machine-learned system in Google Drive that predicts which files a user wants to open. Adding Quick Access recommendations to the Drive homepage cut the amount of time that users spend locating their files in half. Aggregated over the ~1 billion users of Drive, the time saved up adds up to ~1000 work weeks every day. In this paper, we discuss both the challenges of iteratively improving the quality of a personal recommendation system as well as the variety of approaches that we took in order to improve this feature. We explored different deep network architectures, novel modeling techniques, additional data sources, and the effects of latency and biases in the UX. We share both pitfalls as well as successes in our attempts to improve this product, and also discuss how we scaled and managed the complexity of the system. We believe that these insights will be especially useful to those who are working with private corpora as well as those who are building a large-scale production recommendation system.

Many modern recommender systems train their models based on a large amount of implicit user feedback data. Due to the inherent bias in this data (e.g., position bias), learning from it directly can lead to suboptimal models. Recently, unbiased learning was proposed to address such problems by leveraging counterfactual techniques like inverse propensity weighting (IPW). In these methods, propensity scores estimation is usually limited to item's display position in a single user interface (UI).

It is often desirable to model multiple objectives in real-world web applications, such as user satisfaction and user engagement in recommender systems. Multi-task learning has become the standard approach for such applications recently.

Work in information retrieval has traditionally focused on ranking and relevance: given a query, return some number of results ordered by relevance to the user. However, the problem of determining how many results to return, i.e. how to optimally truncate the ranked result list, has received less attention despite being of critical importance in a range of applications. Such truncation is a balancing act between the overall relevance, or usefulness of the results, with the user cost of processing more results. In this work, we propose Choppy, an assumption-free model based on the widely successful Transformer architecture, to the ranked list truncation problem. Needing nothing more than the relevance scores of the results, the model uses a powerful multi-head attention mechanism to directly optimize any user-defined IR metric. We show Choppy improves upon recent state-of-the-art methods.

Retrieval effectiveness in information retrieval systems is heavily dependent on how various parameters are tuned. One option to find these parameters is to run multiple online experiments and using a parameter sweep approach in order to optimize the search system. There are multiple downsides of this approach, mainly that it may lead to a poor experience for users. Another option is to do offline evaluation, which can act as a safeguard against potential quality issues. Offline evaluation requires a validation set of data that can be benchmarked against different parameter settings. However, for search over personal corpora, e.g. email and file search, it is impractical and often impossible to get a complete representative validation set, due to the inability to save raw queries and document information. In this work, we show how to do offline parameter tuning with only a partial validation set. In addition, we demonstrate how to do parameter tuning in the cases when we have complete knowledge of the internal implementation of the search system (white-box tuning), as well as the case where we have only partial knowledge (grey-box tuning). This has allowed us to do offline parameter tuning in a privacy-sensitive manner.

In personal email search, user queries often impose different requirements on different aspects of the retrieved emails. For example, the query "my recent flight to the US" requires emails to be ranked based on both textual contents and recency of the email documents, while other queries such as "medical history" do not impose any constraints on the recency of the email. Recent deep learning-to-rank models for personal email search often directly concatenate dense numerical features (e.g., document age) with embedded sparse features (e.g., n-gram embeddings). In this paper, we first show with a set of experiments on synthetic datasets that direct concatenation of dense and sparse features does not lead to the optimal search performance of deep neural ranking models. To effectively incorporate both sparse and dense email features into personal email search ranking, we propose a novel neural model, SepAttn. SepAttn first builds two separate neural models to learn from sparse and dense features respectively, and then applies an attention mechanism at the prediction level to derive the final prediction from these two models. We conduct a comprehensive set of experiments on a large-scale email search dataset, and demonstrate that our SepAttn model consistently improves the search quality over the baseline models.

Neural search ranking models have been not only actively studied in the information retrieval community, but also widely adopted in real-world industrial applications. However, due to the non-convexity and stochastic training of neural model formulations, the obtained models are unstable in the sense that model predictions can vary a lot for two models trained with the same configuration. In practice, new features are continuously introduced and new model architectures are explored to improve model effectiveness. In these cases, the instability of neural models leads to unnecessary document ranking changes for a large portion of queries. Such changes not only lead to inconsistent user experience, but also add noise to online experimentation and can slow down model improvement cycles. How to stabilize neural search ranking models during model update is an important but largely unexplored problem. Motivated by trigger analysis, we suggest balancing the trade-off between performance improvement and the number of affected queries. Concretely, we formulate it as an optimization problem with the objective as maximizing the average effect over the affected queries. We propose two heuristics and one theory-guided stabilization method to solve the optimization problem. Our proposed methods are evaluated on two of the world’s largest personal search services: Gmail search and Google Drive search. Empirical results show that our proposed methods are very effective in optimizing the proposed objective and are applicable to different model update scenarios.

Recent neural ranking algorithms focus on learning semantic matching between query and document terms. However, practical learning to rank systems typically rely on a wide range of side information beyond query and document textual features, like location, user context, etc. It is common practice to concatenate all of these features and rely on deep models to learn a complex representation.

Decision Trees (DTs) like LambdaMART have been one of the most effective types of learning-to-rank algorithms in the past decade. They typically work well with hand-crafted dense features (e.g., BM25 scores). Recently, Neural Networks (NNs) have shown impressive results in leveraging sparse and complex features (e.g., query and document keywords) directly when a large amount of training data is available. While there is a large body of work on how to use NNs for semantic matching between queries and documents, relatively less work has been conducted to compare NNs with DTs for general learning-to-rank tasks, where dense features are also available and DTs can achieve state-of-the-art performance. In this paper, we study how to combine DTs and NNs to effectively bring the benefits from both sides in the learning-to-rank setting. Specifically, we focus our study on personal search where clicks are used as the primary labels with unbiased learning-to-rank algorithms and a significantly large amount of training data is easily available. Our combination methods are based on ensemble learning. We design 12 variants and compare them based on two aspects, ranking effectiveness and ease-of-deployment, using two of the largest personal search services: Gmail search and Google Drive search. We show that direct application of existing ensemble methods can not achieve both aspects. We thus design a novel method that uses NNs to compensate DTs via boosting. We show that such a method is not only easier to deploy, but also gives comparable or better ranking accuracy.

Traditional online quality metrics are based on search and browsing signals, such as position and time of the click. Such metrics typically model all users' behavior in exactly the same manner. Modeling individuals' behavior in Web search may be challenging as the user's historical behavior may not always be available (e.g., if the user is not signed into a given service). However, in personal search, individual users issue queries over their personal corpus (e.g. emails, files, etc.) while they are logged into the service. This brings an opportunity to calibrate online quality metrics with respect to an individual's search habits. With this goal in mind, the current paper focuses on a user-centric evaluation framework for personal search by taking into account variability of search and browsing behavior across individuals. The main idea is to calibrate each interaction of a user with respect to their historical behavior and search habits. To formalize this, a characterization of online metrics is proposed according to the relevance signal of interest and how the signal contributes to the computation of the gain in a metric. The proposed framework introduces a variant of online metrics called pMetrics (short for personalized metrics) that are based on the average search habits of users for the relevance signal of interest. Through extensive online experiments on a large population of GMail search users, we show that pMetrics are effective in terms of their sensitivity, robustness, and stability compared to their standard variants as well as baselines with different normalization factors.

Synonym expansion is a technique that adds related words to search queries, which may lead to more relevant documents being retrieved, thus improving recall. There is extensive prior work on synonym expansion for web search, however very few studies have tackled its application for email search. Synonym expansion for private corpora like emails poses several unique research challenges. First, the emails are not shared across users, which precludes us from directly employing query-document bipartite graphs, which are standard in web search synonym expansion. Second, user search queries are of personal nature, and may not be generalizable across users. Third, the size of the underlying corpora from which the synonyms may be mined is relatively small (i.e., user's private email inbox) compared to the size of the web corpus. Therefore, in this paper, we propose a solution tailored to the challenges of synonym expansion for email search. We formulate it as a multi-view learning problem, and propose a novel embedding-based model that joins information from multiple sources to obtain the optimal synonym candidates. To demonstrate the effectiveness of the proposed technique, we evaluate our model using both explicit human ratings as well as a live experiment using the Gmail Search service, one of the world's largest email search engines.

In the enterprise email search setting, the same search engine often powers multiple enterprises from various industries: technology, education, manufacturing, etc. However, using the same global ranking model across different enterprises may result in suboptimal search quality, due to the corpora differences and distinct information needs. On the other hand, training an individual ranking model for each enterprise may be infeasible, especially for smaller institutions with limited data. To address this data challenge, in this paper we propose a domain adaptation approach that fine-tunes the global model to each individual enterprise. In particular, we propose a novel application of the Maximum Mean Discrepancy (MMD) approach to information retrieval, which attempts to bridge the gap between the global data distribution and the data distribution for a given individual enterprise. We conduct a comprehensive set of experiments on a large-scale email search engine, and demonstrate that the MMD approach consistently improves the search quality for multiple individual domains, both in comparison to the global ranking model, as well as several competitive domain adaptation baselines including adversarial learning methods.

Spell correction is a must-have feature for any modern search engine in applications such as web or e-commerce search. Typical spell correction solutions used in production systems consist of large indexed lookup tables based on a global model trained across many users over a large scale web corpus or a query log.

User information needs vary significantly across different tasks, and therefore their queries will also differ considerably in their expressiveness and semantics. Many studies have been proposed to model such query diversity by obtaining query types and building query-dependent ranking models. These studies typically require either a labeled query dataset or clicks from multiple users aggregated over the same document. These techniques, however, are not applicable when manual query labeling is not viable, and aggregated clicks are unavailable due to the private nature of the document collection, e.g., in email search scenarios. In this paper, we study how to obtain query type in an unsupervised fashion and how to incorporate this information into query-dependent ranking models. We first develop a hierarchical clustering algorithm based on truncated SVD and varimax rotation to obtain coarse-to-fine query types. Then, we study three query-dependent ranking models, including two neural models that leverage query type information as additional features, and one novel multi-task neural model that views query type as the label for the auxiliary query cluster prediction task. This multi-task model is trained to simultaneously rank documents and predict query types. Our experiments on tens of millions of real-world email search queries demonstrate that the proposed multi-task model can significantly outperform the baseline neural ranking models, which either do not incorporate query type information or just simply feed query type as an additional feature.

A well-known challenge in learning from click data is its inherent bias and most notably position bias. Traditional click models aim to extract the ‹query, document› relevance and the estimated bias is usually discarded after relevance is extracted. In contrast, the most recent work on unbiased learning-to-rank can effectively leverage the bias and thus focuses on estimating bias rather than relevance [20, 31]. Existing approaches use search result randomization over a small percentage of production traffic to estimate the position bias. This is not desired because result randomization can negatively impact users' search experience. In this paper, we compare different schemes for result randomization (i.e., RandTopN and RandPair) and show their negative effect in personal search. Then we study how to infer such bias from regular click data without relying on randomization. We propose a regression-based Expectation-Maximization (EM) algorithm that is based on a position bias click model and that can handle highly sparse clicks in personal search. We evaluate our EM algorithm and the extracted bias in the learning-to-rank setting. Our results show that it is promising to extract position bias from regular clicks without result randomization. The extracted bias can improve the learning-to-rank algorithms significantly. In addition, we compare the pointwise and pairwise learning-to-rank models. Our results show that pairwise models are more effective in leveraging the estimated bias.

User interaction data (e.g., click data) has proven to be a powerful signal for learning-to-rank models in web search. However, such models require observing multiple interactions across many users for the same query-document pair to achieve statistically meaningful gains. Therefore, utilizing user interaction data for improving search over personal, rather than public, content is a challenging problem. First, the documents (e.g., emails or private files) are not shared across users. Second, user search queries are of personal nature (e.g., "alice's address") and may not generalize well across users. In this paper, we propose a solution to these challenges, by projecting user queries and documents into a multi-dimensional space of fine-grained and semantically coherent attributes. We then introduce a novel parameterization technique to overcome sparsity in the multi-dimensional attribute space. Attribute parameterization enables effective usage of cross-user interactions for improving personal search quality -- which is a first such published result, to the best of our knowledge. Experiments with a dataset derived from interactions of users of one of the world's largest personal search engines demonstrate the effectiveness of the proposed attribute parameterization technique.

Click-through data has proven to be a critical resource for improving search ranking quality. Though a large amount of click data can be easily collected by search engines, various biases make it difficult to fully leverage this type of data. In the past, many click models have been proposed and successfully used to estimate the relevance for individual query-document pairs in the context of web search. These click models typically require a large quantity of clicks for each individual pair and this makes them difficult to apply in systems where click data is highly sparse due to personalized corpora and information needs, e.g., personal search. In this paper, we study the problem of how to leverage sparse click data in personal search and introduce a novel selection bias problem and address it in the learning-to-rank framework. This paper proposes a few bias estimation methods, including a novel query-dependent one that captures queries with similar results and can successfully deal with sparse data. We empirically demonstrate that learning-to-rank that accounts for query-dependent selection bias yields significant improvements in search effectiveness through online experiments with one of the world's largest personal search engines.

No abstract available.

Most standard information retrieval models use a single source of information (e.g., the retrieval corpus) for query formulation tasks such as term and phrase weighting and query expansion. In contrast, in this paper, we present a unified framework that automatically optimizes the combination of information sources used for effective query formulation. The proposed framework produces fully weighted and expanded queries that are both more effective and more compact than those produced by the current state-of-the-art query expansion and weighting methods. We conduct an empirical evaluation of our framework for both newswire and web corpora. In all cases, our combination of multiple information sources for query formulation is found to be more effective than using any single source. The proposed query formulations are especially advantageous for large scale web corpora, where they also reduce the number of terms required for effective query expansion, and improve the diversity of the retrieved results.

Previous research has shown that features based on term proximity are important for effective retrieval. However, they incur substantial costs in terms of larger inverted indexes and slower query execution times as compared to term-based features. This paper explores whether term proximity features based on approximate term positions are as effective as those based on exact term positions. We introduce the novel notion of approximate positional indexes based on dividing documents into coarse-grained buckets and recording term positions with respect to those buckets. We propose different approaches to defining the buckets and compactly encoding bucket ids. In the context of linear ranking functions, experimental results show that features based on approximate term positions are able to achieve effectiveness comparable to exact term positions, but with smaller indexes and faster query evaluation.

Test collections are the primary drivers of progress in information retrieval. They provide yardsticks for assessing the effectiveness of ranking functions in an automatic, rapid, and repeatable fashion and serve as training data for learning to rank models. However, manual construction of test collections tends to be slow, labor-intensive, and expensive. This paper examines the feasibility of constructing web search test collections in a completely unsupervised manner given only a large web corpus as input. Within our proposed framework, anchor text extracted from the web graph is treated as a pseudo query log from which pseudo queries are sampled. For each pseudo query, a set of relevant and non-relevant documents are selected using a variety of web-specific features, including spam and aggregated anchor text weights. The automatically mined queries and judgments form a pseudo test collection that can be used for training ranking functions. Experiments carried out on TREC web track data show that learning to rank models trained using pseudo test collections outperform an unsupervised ranking function and are statistically indistinguishable from a model trained using manual judgments, demonstrating the usefulness of our approach in extracting reasonable quality training data "for free".

No abstract available.

The majority of the current information retrieval models weight the query concepts (e.g., terms or phrases) in an unsupervised manner, based solely on the collection statistics. In this paper, we go beyond the unsupervised estimation of concept weights, and propose a parameterized concept weighting model. In our model, the weight of each query concept is determined using a parameterized combination of diverse importance features. Unlike the existing supervised ranking methods, our model learns importance weights not only for the explicit query concepts, but also for the latent concepts that are associated with the query through pseudo-relevance feedback. The experimental results on both newswire and web TREC corpora show that our model consistently and significantly outperforms a wide range of state-of-the-art retrieval models. In addition, our model significantly reduces the number of latent concepts used for query expansion compared to the non-parameterized pseudo-relevance feedback based models.

There is a fundamental tradeoff between effectiveness and efficiency when designing retrieval models for large-scale document collections. Effectiveness tends to derive from sophisticated ranking functions, such as those constructed using learning to rank, while efficiency gains tend to arise from improvements in query evaluation and caching strategies. Given their inherently disjoint nature, it is difficult to jointly optimize effectiveness and efficiency in end-to-end systems. To address this problem, we formulate and develop a novel cascade ranking model, which unlike previous approaches, can simultaneously improve both top k ranked effectiveness and retrieval efficiency. The model constructs a cascade of increasingly complex ranking functions that progressively prunes and refines the set of candidate documents to minimize retrieval latency and maximize result set quality. We present a novel boosting algorithm for learning such cascades to directly optimize the tradeoff between effectiveness and efficiency. Experimental results show that our cascades are faster and return higher quality results than comparable ranking models.

Ranking Web search results has long evolved beyond simple bag-of-words retrieval models. Modern search engines routinely employ machine learning ranking that relies on exogenous relevance signals. Yet the majority of current methods still evaluate each Web page out of context. In this work, we introduce a novel source of relevance information for Web search by evaluating each page in the context of its host Web site. For this purpose, we devise two strategies for compactly representing entire Web sites. We formalize our approach by building two indices, a traditional page index and a new site index, where each "document" represents the an entire Web site. At runtime, a query is first executed against both indices, and then the final page score for a given query is produced by combining the scores of the page and its site. Experimental results carried out on a large-scale Web search test collection from a major commercial search engine confirm the proposed approach leads to consistent and significant improvements in retrieval effectiveness.

Most existing query expansion approaches for ad-hoc retrieval adopt overly simplistic textual representations that treat documents as bags of words and ignore inherent document structure. These simple representations often lead to incorrect independence assumptions in the proposed approaches and result in limited retrieval effectiveness. In this paper, we propose a novel query expansion technique that models the various types of dependencies that exist between original query terms and expansion terms within a robust, unified framework. The proposed model is called Hierarchical Markov random fields (HMRFs), based on Latent Concept Expansion (LCE). By exploiting implicit (or explicit) hierarchical structure within documents, HMRFs can incorporate hierarchical interactions which are important for modeling term dependencies in an efficient manner. Our rigorous experimental evaluation carried out using several TREC data sets shows that our proposed query expansion technique consistently and significantly outperforms the current state-of-the-art query expansion approaches, including relevance-based language models and LCE.

This paper introduces the notion of temporally constrained ranked retrieval, which, given a query and a time constraint, produces the best possible ranked list within the specified time limit. Naturally, more time should translate into better results, but the ranking algorithm should always produce some results. This property is desirable from a number of perspectives: to cope with diverse users and information needs, as well as to better manage system load and variance in query execution times. We propose two temporally constrained ranking algorithms based on a class of probabilistic prediction models that can naturally incorporate efficiency constraints: one that makes independent feature selection decisions, and the other that makes joint feature selection decisions. Experiments on three different test collections show that both ranking algorithms are able to satisfy imposed time constraints, although the joint model outperforms the independent model in being able to deliver more effective results, especially under tight time constraints, due to its ability to capture feature dependencies.

Match-making systems refer to systems where users want to meet other individuals to satisfy some underlying need. Examples of match-making systems include dating services, resume/job bulletin boards, community based question answering, and consumer-to-consumer marketplaces. One fundamental component of a match-making system is the retrieval and ranking of candidate matches for a given user. We present the first in-depth study of information retrieval approaches applied to match-making systems. Specifically, we focus on retrieval for a dating service. This domain offers several unique problems not found in traditional information retrieval tasks. These include two-sided relevance, very subjective relevance, extremely few relevant matches, and structured queries. We propose a machine learned ranking function that makes use of features extracted from the uniquely rich user profiles that consist of both structured and unstructured attributes. An extensive evaluation carried out using data gathered from a real online dating service shows the benefits of our proposed methodology with respect to traditional match-making baseline systems. Our analysis also provides deep insights into the aspects of match-making that are particularly important for producing highly relevant matches.

It has been shown that learning to rank approaches are capable of learning highly effective ranking functions. However, these approaches have mostly ignored the important issue of efficiency. Given that both efficiency and effectiveness are important for real search engines, models that are optimized for effectiveness may not meet the strict efficiency requirements necessary to deploy in a production environment. In this work, we present a unified framework for jointly optimizing effectiveness and efficiency. We propose new metrics that capture the tradeoff between these two competing forces and devise a strategy for automatically learning models that directly optimize the tradeoff metrics. Experiments indicate that models learned in this way provide a good balance between retrieval effectiveness and efficiency. With specific loss functions, learned models converge to familiar existing ones, which demonstrates the generality of our framework. Finally, we show that our approach naturally leads to a reduction in the variance of query execution times, which is important for query load balancing and user satisfaction.

Modeling query concepts through term dependencies has been shown to have a significant positive effect on retrieval performance, especially for tasks such as web search, where relevance at high ranks is particularly critical. Most previous work, however, treats all concepts as equally important, an assumption that often does not hold, especially for longer, more complex queries. In this paper, we show that one of the most effective existing term dependence models can be naturally extended by assigning weights to concepts. We demonstrate that the weighted dependence model can be trained using existing learning-to-rank techniques, even with a relatively small number of training queries. Our study compares the effectiveness of both endogenous (collection-based) and exogenous (based on external sources) features for determining concept importance. To test the weighted dependence model, we perform experiments on both publicly available TREC corpora and a proprietary web corpus. Our experimental results indicate that our model consistently and significantly outperforms both the standard bag-of-words model and the unweighted term dependence model, and that combining endogenous and exogenous features generally results in the best retrieval effectiveness.

While test collection construction is a time-consuming and expensive process, the true cost is amortized by reusing the collection over hundreds or thousands of experiments. Some of these experiments may involve systems that retrieve documents not judged during the initial construction phase, and some of these systems may be "hard" to evaluate: depending on which judgments are missing and which judged documents were retrieved, the experimenter's confidence in an evaluation could potentially be very low. We propose two methods for quantifying the reusability of a test collection for evaluating new systems. The proposed methods provide simple yet highly effective tests for determining whether an existing set of judgments is useful for evaluating a new system. Empirical evaluations using TREC datasets confirm the usefulness of our proposed reusability measures. In particular, we show that our methods can reliably estimate confidence intervals that are indicative of collection reusability.

The core task of sponsored search is to retrieve relevant ads for the user's query. Ads can be retrieved either by exact match, when their bid term is identical to the query, or by advanced match, which indexes ads as documents and is similar to standard information retrieval (IR). Recently, there has been a great deal of research into developing advanced match ranking algorithms. However, no previous research has addressed the ad indexing problem. Unlike most traditional search problems, the ad corpus is defined hierarchically in terms of advertiser accounts, campaigns, and ad groups, which further consist of creatives and bid terms. This hierarchical structure makes indexing highly non-trivial, as naively indexing all possible displayable ads leads to a prohibitively large and ineffective index. We show that ad retrieval using such an index is not only slow, but its precision is suboptimal as well. We investigate various strategies for compact, hierarchy-aware indexing of sponsored search ads through adaptation of standard IR indexing techniques. We also propose a new ad retrieval method that yields more relevant ads by exploiting the structured nature of the ad corpus. Experiments carried out over a large ad test collection from a commercial search engine show that our proposed methods are highly effective and efficient compared to more standard indexing and retrieval approaches.

No abstract available.

It is well known that anchor text plays a critical role in a variety of search tasks performed over hypertextual domains, including enterprise search, wiki search, and web search. It is common practice to enrich a document's standard textual representation with all of the anchor text associated with its incoming hyperlinks. However, this approach does not help match relevant pages with very few inlinks. In this paper, we propose a method for overcoming anchor text sparsity by enriching document representations with anchor text that has been aggregated across the hyperlink graph. This aggregation mechanism acts to smooth, or diffuse, anchor text within a domain. We rigorously evaluate our proposed approach on a large web search test collection. Our results show the approach significantly improves retrieval effectiveness, especially for longer, more difficult queries.

Sponsored search systems are tasked with matching queries

Web textual advertising can be interpreted as a search problem over the corpus of ads available for display in a particular context. In contrast to conventional information retrieval systems, which always return results if the corpus contains any documents lexically related to the query, in Web advertising it is acceptable, and occasionally even desirable, not to show any results. When no ads are relevant to the user's interests, then showing irrelevant ads should be avoided since they annoy the user and produce no economic benefit. In this paper we pose a decision problem to swing, that is, whether or not to show any of the ads for the incoming request. We propose two methods for addressing this problem, a simple thresholding approach and a machine learning approach, which collectively analyzes the set of candidate ads augmented with external knowledge. Our experimental evaluation, based on over 28,000 editorial judgments, shows that we are able to predict, with high accuracy, when to swing for both content match and sponsored search advertising.

Inverse document frequency (IDF) is one of the most useful and widely used concepts in information retrieval. There have been various attempts to provide theoretical justifications for IDF. One of the most appealing derivations follows from the Robertson-Sparck Jones relevance weight. However, this derivation, and others related to it, typically make a number of strong assumptions that are often glossed over. In this paper, we re-examine these assumptions from a Bayesian perspective, discuss possible alternatives, and derive a new, more generalized form of IDF that we call generalized inverse document frequency. In addition to providing theoretical insights into IDF, we also undertake a rigorous empirical evaluation that shows generalized IDF outperforms classical versions of IDF on a number of ad hoc retrieval tasks.

Previous applications of the Markov random field model for information retrieval have used manually chosen features. However, it is often difficult or impossible to know, a priori, the best set of features to use for a given task or data set. Therefore, there is a need to develop automatic feature selection techniques. In this paper we describe a greedy procedure for automatically selecting features to use within the Markov random field model for information retrieval. We also propose a novel, robust method for describing classes of textual information retrieval features. Experimental results, evaluated on standard TREC test collections, show that our feature selection algorithm produces models that are either significantly more effective than, or equally effective as, models with manually selected features, such as those used in the past.

No abstract available.

Query expansion, in the form of pseudo-relevance feedback or relevance feedback, is a common technique used to improve retrieval effectiveness. Most previous approaches have ignored important issues, such as the role of features and the importance of modeling term dependencies. In this paper, we propose a robust query expansion technique based onthe Markov random field model for information retrieval. The technique, called latent concept expansion, provides a mechanism for modeling term dependencies during expansion. Furthermore, the use of arbitrary features within the model provides a powerful framework for going beyond simple term occurrence features that are implicitly used by most other expansion techniques. We evaluate our technique against relevance models, a state-of-the-art language modeling query expansion technique. Our model demonstrates consistent and significant improvements in retrieval effectiveness across several TREC data sets. We also describe how our technique can be used to generate meaningful multi-term concepts for tasks such as query suggestion/reformulation.

In this work we investigate three important aspects of parameterized retrieval models: estimation, sensitivity, and generalization. Since all parameterized models, even those based on heuristics, have inherent uncertainty, we study these issues using statistical tools.

Information retrieval algorithms leverage various collection statistics to improve performance. Because these statistics are often computed on a relatively small evaluation corpus, we believe using larger, non-evaluation corpora should improve performance. Specifically, we advocate incorporating external corpora based on language modeling. We refer to this process as external expansion. When compared to traditional pseudo-relevance feedback techniques, external expansion is more stable across topics and up to 10% more effective in terms of mean average precision. Our results show that using a high quality corpus that is comparable to the evaluation corpus can be as, if not more, effective than using the web. Our results also show that external expansion outperforms simulated relevance feedback. In addition, we propose a method for predicting the extent to which external expansion will improve retrieval performance. Our new measure demonstrates positive correlation with improvements in mean average precision.

Text similarity spans a spectrum, with broad topical similarity near one extreme and document identity at the other. Intermediate levels of similarity -- resulting from summarization, paraphrasing, copying, and stronger forms of topical relevance -- are useful for applications such as information flow analysis and question-answering tasks. In this paper, we explore mechanisms for measuring such intermediate kinds of similarity, focusing on the task of identifying where a particular piece of information originated. We consider both sentence-to-sentence and document-to-document comparison, and have incorporated these algorithms into RECAP, a prototype information flow analysis tool. Our experimental results with RECAP indicate that new mechanisms such as those we propose are likely to be more appropriate than existing methods for identifying the intermediate forms of similarity.

No abstract available.

This paper develops a general, formal framework for modeling term dependencies via Markov random fields. The model allows for arbitrary text features to be incorporated as evidence. In particular, we make use of features based on occurrences of single terms, ordered phrases, and unordered phrases. We explore full independence, sequential dependence, and full dependence variants of the model. A novel approach is developed to train the model that directly maximizes the mean average precision rather than maximizing the likelihood of the training data. Ad hoc retrieval experiments are presented on several newswire and web collections, including the GOV2 collection used at the TREC 2004 Terabyte Track. The results show significant improvements are possible by modeling dependencies, especially on the larger web collections.

No abstract available.