arXiv subjects

Charles L. A. Clarke

Publications and source records attributed to Charles L. A. Clarke.

47 records · Page 3Linked to original sources

arXiv2022

Human Preferences as Dueling Bandits

The dramatic improvements in core information retrieval tasks engendered by neural rankers create a need for novel evaluation methods. If every ranker returns highly relevant items in the top ranks, it becomes difficult to recognize meaningful differences between them and to build reusable test collections. Several recent papers explore pairwise preference judgments as an alternative to traditional graded relevance assessments. Rather than viewing items one at a time, assessors view items side-by-side and indicate the one that provides the better response to a query, allowing fine-grained distinctions. If we employ preference judgments to identify the probably best items for each query, we can measure rankers by their ability to place these items as high as possible. We frame the problem of finding best items as a dueling bandits problem. While many papers explore dueling bandits for online ranker evaluation via interleaving, they have not been considered as a framework for offline evaluation via human preference judgments. We review the literature for possible solutions. For human preference judgments, any usable algorithm must tolerate ties, since two items may appear nearly equal to assessors, and it must minimize the number of judgments required for any specific pair, since each such comparison requires an independent assessor. Since the theoretical guarantees provided by most algorithms depend on assumptions that are not satisfied by human preference judgments, we simulate selected algorithms on representative test cases to provide insight into their practical utility. Based on these simulations, one algorithm stands out for its potential. Our simulations suggest modifications to further improve its performance. Using the modified algorithm, we collect over 10,000 preference judgments for submissions to the TREC 2021 Deep Learning Track, confirming its suitability.

cs.IR↗

arXiv2022

Shallow pooling for sparse labels

Recent years have seen enormous gains in core IR tasks, including document and passage ranking. Datasets and leaderboards, and in particular the MS MARCO datasets, illustrate the dramatic improvements achieved by modern neural rankers. When compared with traditional test collections, the MS MARCO datasets employ substantially more queries with substantially fewer known relevant items per query. Given the sparsity of these relevance labels, the MS MARCO leaderboards track improvements with mean reciprocal rank (MRR). In essence, a relevant item is treated as the "right answer", with rankers scored on their ability to place this item high in the ranking. In working with these sparse labels, we have observed that the top items returned by a ranker often appear superior to judged relevant items. To test this observation, we employed crowdsourced workers to make preference judgments between the top item returned by a modern neural ranking stack and a judged relevant item. The results support our observation. If we imagine a perfect ranker under MRR, with a score of 1 on all queries, our preference judgments indicate that a searcher would prefer the top result from a modern neural ranking stack more frequently than the top result from the imaginary perfect ranker, making our neural ranker "better than perfect". To understand the implications for the leaderboard, we pooled the top document from available runs near the top of the passage ranking leaderboard for over 500 queries. We employed crowdsourced workers to make preference judgments over these pools and re-evaluated the runs. Our results support our concerns that current MS MARCO datasets may no longer be able to recognize genuine improvements in rankers. In future, if rankers are measured against a single "right answer", this answer should be the best answer or most preferred answer, and maintained with ongoing judgments.

cs.IR↗

arXiv2021

Translating Human Mobility Forecasting through Natural Language Generation

Existing human mobility forecasting models follow the standard design of the time-series prediction model which takes a series of numerical values as input to generate a numerical value as a prediction. Although treating this as a regression problem seems straightforward, incorporating various contextual information such as the semantic category information of each Place-of-Interest (POI) is a necessary step, and often the bottleneck, in designing an effective mobility prediction model. As opposed to the typical approach, we treat forecasting as a translation problem and propose a novel forecasting through a language generation pipeline. The paper aims to address the human mobility forecasting problem as a language translation task in a sequence-to-sequence manner. A mobility-to-language template is first introduced to describe the numerical mobility data as natural language sentences. The core intuition of the human mobility forecasting translation task is to convert the input mobility description sentences into a future mobility description from which the prediction target can be obtained. Under this pipeline, a two-branch network, SHIFT (Translating Human Mobility Forecasting), is designed. Specifically, it consists of one main branch for language generation and one auxiliary branch to directly learn mobility patterns. During the training, we develop a momentum mode for better connecting and training the two branches. Extensive experiments on three real-world datasets demonstrate that the proposed SHIFT is effective and presents a new revolutionary approach to forecasting human mobility.

cs.CL↗

arXiv2021

Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection

Over the last few years, contextualized pre-trained transformer models such as BERT have provided substantial improvements on information retrieval tasks. Recent approaches based on pre-trained transformer models such as BERT, fine-tune dense low-dimensional contextualized representations of queries and documents in embedding space. While these dense retrievers enjoy substantial retrieval effectiveness improvements compared to sparse retrievers, they are computationally intensive, requiring substantial GPU resources, and dense retrievers are known to be more expensive from both time and resource perspectives. In addition, sparse retrievers have been shown to retrieve complementary information with respect to dense retrievers, leading to proposals for hybrid retrievers. These hybrid retrievers leverage low-cost, exact-matching based sparse retrievers along with dense retrievers to bridge the semantic gaps between query and documents. In this work, we address this trade-off between the cost and utility of sparse vs dense retrievers by proposing a classifier to select a suitable retrieval strategy (i.e., sparse vs. dense vs. hybrid) for individual queries. Leveraging sparse retrievers for queries which can be answered with sparse retrievers decreases the number of calls to GPUs. Consequently, while utility is maintained, query latency decreases. Although we use less computational resources and spend less time, we still achieve improved performance. Our classifier can select between sparse and dense retrieval strategies based on the query alone. We conduct experiments on the MS MARCO passage dataset demonstrating an improved range of efficiency/effectiveness trade-offs between purely sparse, purely dense or hybrid retrieval strategies, allowing an appropriate strategy to be selected based on a target latency and resource budget.

cs.IR↗

arXiv2021

Assessing top-$k$ preferences

Assessors make preference judgments faster and more consistently than graded judgments. Preference judgments can also recognize distinctions between items that appear equivalent under graded judgments. Unfortunately, preference judgments can require more than linear effort to fully order a pool of items, and evaluation measures for preference judgments are not as well established as those for graded judgments, such as NDCG. In this paper, we explore the assessment process for partial preference judgments, with the aim of identifying and ordering the top items in the pool, rather than fully ordering the entire pool. To measure the performance of a ranker, we compare its output to this preferred ordering by applying a rank similarity measure.We demonstrate the practical feasibility of this approach by crowdsourcing partial preferences for the TREC 2019 Conversational Assistance Track, replacing NDCG with a new measure named "compatibility". This new measure has its most striking impact when comparing modern neural rankers, where it is able to recognize significant improvements in quality that would otherwise be missed by NDCG.

cs.IR↗

arXiv2017

Efficient and Effective Tail Latency Minimization in Multi-Stage Retrieval Systems

Scalable web search systems typically employ multi-stage retrieval architectures, where an initial stage generates a set of candidate documents that are then pruned and re-ranked. Since subsequent stages typically exploit a multitude of features of varying costs using machine-learned models, reducing the number of documents that are considered at each stage improves latency. In this work, we propose and validate a unified framework that can be used to predict a wide range of performance-sensitive parameters which minimize effectiveness loss, while simultaneously minimizing query latency, across all stages of a multi-stage search architecture. Furthermore, our framework can be easily applied in large-scale IR systems, can be trained without explicitly requiring relevance judgments, and can target a variety of different efficiency-effectiveness trade-offs, making it well suited to a wide range of search scenarios. Our results show that we can reliably predict a number of different parameters on a per-query basis, while simultaneously detecting and minimizing the likelihood of tail-latency queries that exceed a pre-specified performance budget. As a proof of concept, we use the prediction framework to help alleviate the problem of tail-latency queries in early stage retrieval. On the standard ClueWeb09B collection and 31k queries, we show that our new hybrid system can reliably achieve a maximum query time of 200 ms with a 99.99% response time guarantee without a significant loss in overall effectiveness. The solutions presented are practical, and can easily be used in large-scale distributed search engine deployments with a small amount of additional overhead.

cs.IR↗

arXiv2016

Ten Blue Links on Mars

This paper explores a simple question: How would we provide a high-quality search experience on Mars, where the fundamental physical limit is speed-of-light propagation delays on the order of tens of minutes? On Earth, users are accustomed to nearly instantaneous response times from search engines. Is it possible to overcome orders-of-magnitude longer latency to provide a tolerable user experience on Mars? In this paper, we formulate the searching from Mars problem as a tradeoff between "effort" (waiting for responses from Earth) and "data transfer" (pre-fetching or caching data on Mars). The contribution of our work is articulating this design space and presenting two case studies that explore the effectiveness of baseline techniques, using publicly available data from the TREC Total Recall and Sessions Tracks. We intend for this research problem to be aspirational and inspirational - even if one is not convinced by the premise of Mars colonization, there are Earth-based scenarios such as searching from a rural village in India that share similar constraints, thus making the problem worthy of exploration and attention from researchers.

cs.IR↗

arXiv2016

Dynamic Trade-Off Prediction in Multi-Stage Retrieval Systems

Modern multi-stage retrieval systems are comprised of a candidate generation stage followed by one or more reranking stages. In such an architecture, the quality of the final ranked list may not be sensitive to the quality of initial candidate pool, especially in terms of early precision. This provides several opportunities to increase retrieval efficiency without significantly sacrificing effectiveness. In this paper, we explore a new approach to dynamically predicting two different parameters in the candidate generation stage which can directly affect the overall efficiency and effectiveness of the entire system. Previous work exploring this tradeoff has focused on global parameter settings that apply to all queries, even though optimal settings vary across queries. In contrast, we propose a technique which makes a parameter prediction that maximizes efficiency within a effectiveness envelope on a per query basis, using only static pre-retrieval features. The query-specific tradeoff point between effectiveness and efficiency is decided using a classifier cascade that weighs possible efficiency gains against effectiveness losses over a range of possible parameter cutoffs to make the prediction. The interesting twist in our new approach is to train classifiers without requiring explicit relevance judgments. We show that our framework is generalizable by applying it to two different retrieval parameters - selecting k in common top-k query retrieval algorithms, and setting a quality threshold, $ρ$, for score-at-a-time approximate query evaluation algorithms. Experimental results show that substantial efficiency gains are achievable depending on the dynamic parameter choice. In addition, our framework provides a versatile tool that can be used to estimate the effectiveness-efficiency tradeoffs that are possible before selecting and tuning algorithms to make machine learned predictions.

cs.IR↗

arXiv2016

The Effects of Latency Penalties in Evaluating Push Notification Systems

We examine the effects of different latency penalties in the evaluation of push notification systems, as operationalized in the TREC 2015 Microblog track evaluation. The purpose of this study is to inform the design of metrics for the TREC 2016 Real-Time Summarization track, which is largely modeled after the TREC 2015 evaluation design.

cs.IR↗

arXiv2015

Assessing Efficiency-Effectiveness Tradeoffs in Multi-Stage Retrieval Systems Without Using Relevance Judgments

Large-scale retrieval systems are often implemented as a cascading sequence of phases -- a first filtering step, in which a large set of candidate documents are extracted using a simple technique such as Boolean matching and/or static document scores; and then one or more ranking steps, in which the pool of documents retrieved by the filter is scored more precisely using dozens or perhaps hundreds of different features. The documents returned to the user are then taken from the head of the final ranked list. Here we examine methods for measuring the quality of filtering and preliminary ranking stages, and show how to use these measurements to tune the overall performance of the system. Standard top-weighted metrics used for overall system evaluation are not appropriate for assessing filtering stages, since the output is a set of documents, rather than an ordered sequence of documents. Instead, we use an approach in which a quality score is computed based on the discrepancy between filtered and full evaluation. Unlike previous approaches, our methods do not require relevance judgments, and thus can be used with virtually any query set. We show that this quality score directly correlates with actual differences in measured effectiveness when relevance judgments are available. Since the quality score does not require relevance judgments, it can be used to identify queries that perform particularly poorly for a given filter. Using these methods, we explore a wide range of filtering options using thousands of queries, categorize the relative merits of the different approaches, and identify useful parameter combinations.

cs.IR↗

arXiv2010

Efficient and Effective Spam Filtering and Re-ranking for Large Web Datasets

The TREC 2009 web ad hoc and relevance feedback tasks used a new document collection, the ClueWeb09 dataset, which was crawled from the general Web in early 2009. This dataset contains 1 billion web pages, a substantial fraction of which are spam --- pages designed to deceive search engines so as to deliver an unwanted payload. We examine the effect of spam on the results of the TREC 2009 web ad hoc and relevance feedback tasks, which used the ClueWeb09 dataset. We show that a simple content-based classifier with minimal training is efficient enough to rank the "spamminess" of every page in the dataset using a standard personal computer in 48 hours, and effective enough to yield significant and substantive improvements in the fixed-cutoff precision (estP10) as well as rank measures (estR-Precision, StatMAP, MAP) of nearly all submitted runs. Moreover, using a set of "honeypot" queries the labeling of training data may be reduced to an entirely automatic process. The results of classical information retrieval methods are particularly enhanced by filtering --- from among the worst to among the best.

cs.IR↗