共查询到20条相似文献，搜索用时 625 毫秒
1.
This article introduces a new language-independent approach for creating a large-scale high-quality test collection of tweets that supports multiple information retrieval (IR) tasks without running a shared-task campaign. The adopted approach (demonstrated over Arabic tweets) designs the collection around significant (i.e., popular) events, which enables the development of topics that represent frequent information needs of Twitter users for which rich content exists. That inherently facilitates the support of multiple tasks that generally revolve around events, namely event detection, ad-hoc search, timeline generation, and real-time summarization. The key highlights of the approach include diversifying the judgment pool via interactive search and multiple manually-crafted queries per topic, collecting high-quality annotations via crowd-workers for relevancy and in-house annotators for novelty, filtering out low-agreement topics and inaccessible tweets, and providing multiple subsets of the collection for better availability. Applying our methodology on Arabic tweets resulted in EveTAR, the first freely-available tweet test collection for multiple IR tasks. EveTAR includes a crawl of 355M Arabic tweets and covers 50 significant events for which about 62K tweets were judged with substantial average inter-annotator agreement (Kappa value of 0.71). We demonstrate the usability of EveTAR by evaluating existing algorithms in the respective tasks. Results indicate that the new collection can support reliable ranking of IR systems that is comparable to similar TREC collections, while providing strong baseline results for future studies over Arabic tweets. 相似文献
2.
Travis Gagie Aleksi Hartikainen Kalle Karhu Juha Kärkkäinen Gonzalo Navarro Simon J. Puglisi Jouni Sirén 《Information Retrieval》2017,20(3):253-291
Most of the fastest-growing string collections today are repetitive, that is, most of the constituent documents are similar to many others. As these collections keep growing, a key approach to handling them is to exploit their repetitiveness, which can reduce their space usage by orders of magnitude. We study the problem of indexing repetitive string collections in order to perform efficient document retrieval operations on them. Document retrieval problems are routinely solved by search engines on large natural language collections, but the techniques are less developed on generic string collections. The case of repetitive string collections is even less understood, and there are very few existing solutions. We develop two novel ideas, interleaved LCPs and precomputed document lists, that yield highly compressed indexes solving the problem of document listing (find all the documents where a string appears), top-k document retrieval (find the k documents where a string appears most often), and document counting (count the number of documents where a string appears). We also show that a classical data structure supporting the latter query becomes highly compressible on repetitive data. Finally, we show how the tools we developed can be combined to solve ranked conjunctive and disjunctive multi-term queries under the simple \({\textsf{tf}}{\textsf{-}}{\textsf{idf}}\) model of relevance. We thoroughly evaluate the resulting techniques in various real-life repetitiveness scenarios, and recommend the best choices for each case. 相似文献
3.
The evaluation of diversified web search results is a relatively new research topic and is not as well-understood as the time-honoured evaluation methodology of traditional IR based on precision and recall. In diversity evaluation, one topic may have more than one intent, and systems are expected to balance relevance and diversity. The recent NTCIR-9 evaluation workshop launched a new task called INTENT which included a diversified web search subtask that differs from the TREC web diversity task in several aspects: the choice of evaluation metrics, the use of intent popularity and per-intent graded relevance, and the use of topic sets that are twice as large as those of TREC. The objective of this study is to examine whether these differences are useful, using the actual data recently obtained from the NTCIR-9 INTENT task. Our main experimental findings are: (1) The $\hbox{D}\,\sharp$ evaluation framework used at NTCIR provides more “intuitive” and statistically reliable results than Intent-Aware Expected Reciprocal Rank; (2) Utilising both intent popularity and per-intent graded relevance as is done at NTCIR tends to improve discriminative power, particularly for $\hbox{D}\,\sharp$ -nDCG; and (3) Reducing the topic set size, even by just 10 topics, can affect not only significance testing but also the entire system ranking; when 50 topics are used (as in TREC) instead of 100 (as in NTCIR), the system ranking can be substantially different from the original ranking and the discriminative power can be halved. These results suggest that the directions being explored at NTCIR are valuable. 相似文献
4.
Modern retrieval test collections are built through a process called pooling in which only a sample of the entire document
set is judged for each topic. The idea behind pooling is to find enough relevant documents such that when unjudged documents
are assumed to be nonrelevant the resulting judgment set is sufficiently complete and unbiased. Yet a constant-size pool represents
an increasingly small percentage of the document set as document sets grow larger, and at some point the assumption of approximately
complete judgments must become invalid. This paper shows that the judgment sets produced by traditional pooling when the pools
are too small relative to the total document set size can be biased in that they favor relevant documents that contain topic
title words. This phenomenon is wholly dependent on the collection size and does not depend on the number of relevant documents
for a given topic. We show that the AQUAINT test collection constructed in the recent TREC 2005 workshop exhibits this biased
relevance set; it is likely that the test collections based on the much larger GOV2 document set also exhibit the bias. The
paper concludes with suggested modifications to traditional pooling and evaluation methodology that may allow very large reusable
test collections to be built.
相似文献
| Ellen VoorheesEmail: |
5.
On information retrieval metrics designed for evaluation with incomplete relevance assessments 总被引：1，自引：0，他引：1
Modern information retrieval (IR) test collections have grown in size, but the available manpower for relevance assessments
has more or less remained constant. Hence, how to reliably evaluate and compare IR systems using incomplete relevance data, where many documents exist that were never examined by the relevance assessors, is receiving a lot of attention.
This article compares the robustness of IR metrics to incomplete relevance assessments, using four different sets of graded-relevance
test collections with submitted runs—the TREC 2003 and 2004 robust track data and the NTCIR-6 Japanese and Chinese IR data
from the crosslingual task. Following previous work, we artificially reduce the original relevance data to simulate IR evaluation
environments with extremely incomplete relevance data. We then investigate the effect of this reduction on discriminative power, which we define as the proportion of system pairs with a statistically significant difference for a given probability of
Type I Error, and on Kendall’s rank correlation, which reflects the overall resemblance of two system rankings according to two different metrics or two different relevance
data sets. According to these experiments, Q′, nDCG′ and AP′ proposed by Sakai are superior to bpref proposed by Buckley and
Voorhees and to Rank-Biased Precision proposed by Moffat and Zobel. We also point out some weaknesses of bpref and Rank-Biased
Precision by examining their formal definitions.
相似文献
| Noriko KandoEmail: |
7.
8.
Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification. However, the effect of the configuration used to generate the word embeddings on the classification performance has not been studied in the existing literature. In this paper, using a Twitter election classification task that aims to detect election-related tweets, we investigate the impact of the background dataset used to train the embedding models, as well as the parameters of the word embedding training process, namely the context window size, the dimensionality and the number of negative samples, on the attained classification performance. By comparing the classification results of word embedding models that have been trained using different background corpora (e.g. Wikipedia articles and Twitter microposts), we show that the background data should align with the Twitter classification dataset both in data type and time period to achieve significantly better performance compared to baselines such as SVM with TF-IDF. Moreover, by evaluating the results of word embedding models trained using various context window sizes and dimensionalities, we find that large context window and dimension sizes are preferable to improve the performance. However, the number of negative samples parameter does not significantly affect the performance of the CNN classifiers. Our experimental results also show that choosing the correct word embedding model for use with CNN leads to statistically significant improvements over various baselines such as random, SVM with TF-IDF and SVM with word embeddings. Finally, for out-of-vocabulary (OOV) words that are not available in the learned word embedding models, we show that a simple OOV strategy to randomly initialise the OOV words without any prior knowledge is sufficient to attain a good classification performance among the current OOV strategies (e.g. a random initialisation using statistics of the pre-trained word embedding models). 相似文献
9.
Iain Stevenson 《Publishing Research Quarterly》2008,24(4):277-284
This paper reviews the current status of the Anglophone (Anglo-American) publishing business and draws some comparisons with publishing in other languages. It then critically reviews the impact of the Harry Potter phenomenon and the questionable progress of e-books in the trade sector, using the example of Stephen King’s Riding the Bullet. It also comments on Amazon’s introduction of the Kindle e-book reader. 相似文献
10.
Caio Moura Daoud Edleno Silva de Moura David Fernandes Altigran Soares da Silva Cristian Rossi Andre Carvalho 《Information Retrieval》2017,20(3):292-316
In this paper, we present Waves, a novel document-at-a-time algorithm for fast computing of top-k query results in search systems. The Waves algorithm uses multi-tier indexes for processing queries. It performs successive tentative evaluations of results which we call waves. Each wave traverses the index, starting from a specific tier level i. Each wave i may insert only those documents that occur in that tier level into the answer. After processing a wave, the algorithm checks whether the answer achieved might be changed by successive waves or not. A new wave is started only if it has a chance of changing the top-k scores. We show through experiments that such lazy query processing strategy results in smaller query processing times when compared to previous approaches proposed in the literature. We present experiments to compare Waves’ performance to the state-of-the-art document-at-a-time query processing methods that preserve top-k results and show scenarios where the method can be a good alternative algorithm for computing top-k results. 相似文献
11.
Kezban Dilek Onal Ye Zhang Ismail Sengor Altingovde Md Mustafizur Rahman Pinar Karagoz Alex Braylan Brandon Dang Heng-Lu Chang Henna Kim Quinten McNamara Aaron Angert Edward Banner Vivek Khetan Tyler McDonnell An Thanh Nguyen Dan Xu Byron C. Wallace Maarten de Rijke Matthew Lease 《Information Retrieval》2018,21(2-3):111-182
A recent “third wave” of neural network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, work in this area is often referred to as deep learning. Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created. In this paper, we survey the current landscape of Neural IR research, paying special attention to the use of learned distributed representations of textual units. We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research. 相似文献
12.
Batch IR evaluations are usually performed in a framework that consists of a document collection, a set of queries, a set of relevance judgments, and one or more effectiveness metrics. A large number of evaluation metrics have been proposed, with two primary families having emerged: recall-based metrics, and utility-based metrics. In both families, the pragmatics of forming judgments mean that it is usual to evaluate the metric to some chosen depth such as \(k=20\) or \(k=100\), without necessarily fully considering the ramifications associated with that choice. Our aim is this paper is to explore the relative risks arising with fixed-depth evaluation in the two families, and document the complex interplay between metric evaluation depth and judgment pooling depth. Using a range of TREC resources including NewsWire data and the ClueWeb collection, we: (1) examine the implications of finite pooling on the subsequent usefulness of different test collections, including specifying options for truncated evaluation; and (2) determine the extent to which various metrics correlate with themselves when computed to different evaluation depths using those judgments. We demonstrate that the judgment pools constructed for the ClueWeb collections lack resilience, and are suited primarily to the application of top-heavy utility-based metrics rather than recall-based metrics; and that on the majority of the established test collections, and across a range of evaluation depths, recall-based metrics tend to be more volatile in the system rankings they generate than are utility-based metrics. That is, experimentation using utility-based metrics is more robust to choices such as the evaluation depth employed than is experimentation using recall-based metrics. This distinction should be noted by researchers as they plan and execute system-versus-system retrieval experiments. 相似文献
13.
Xu Zhuang Yan Zhu Chin-Chen Chang Qiang Peng Faisal Khurshid 《Information Retrieval》2017,20(6):547-574
Web spam pages exploit the biases of search engine algorithms to get higher than their deserved rankings in search results by using several types of spamming techniques. Many web spam demotion algorithms have been developed to combat spam via the use of the web link structure, from which the goodness or badness score of each web page is evaluated. Those scores are then used to identify spam pages or punish their rankings in search engine results. However, most of the published spam demotion algorithms differ from their base models by only very limited improvements and still suffer from some common score manipulation methods. The lack of a general framework for this field makes the task of designing high-performance spam demotion algorithms very inefficient. In this paper, we propose a unified score propagation model for web spam demotion algorithms by abstracting the score propagation process of relevant models with a forward score propagation function and a backward score propagation function, each of which can further be expressed as three sub-functions: a splitting function, an accepting function and a combination function. On the basis of the proposed model, we develop two new web spam demotion algorithms named Supervised Forward and Backward score Ranking (SFBR) and Unsupervised Forward and Backward score Ranking (UFBR). Our experiments, conducted on three large-scale public datasets, show that (1) SFBR is very robust and apparently outperforms other algorithms and (2) UFBR can obtain results comparable to some well-known supervised algorithms in the spam demotion task even if the UFBR is unsupervised. 相似文献
14.
Automatic detection of source code plagiarism is an important research field for both the commercial software industry and within the research community. Existing methods of plagiarism detection primarily involve exhaustive pairwise document comparison, which does not scale well for large software collections. To achieve scalability, we approach the problem from an information retrieval (IR) perspective. We retrieve a ranked list of candidate documents in response to a pseudo-query representation constructed from each source code document in the collection. The challenge in source code document retrieval is that the standard bag-of-words (BoW) representation model for such documents is likely to result in many false positives being retrieved, because of the use of identical programming language specific constructs and keywords. To address this problem, we make use of an abstract syntax tree (AST) representation of the source code documents. While the IR approach is efficient, it is essentially unsupervised in nature. To further improve its effectiveness, we apply a supervised classifier (pre-trained with features extracted from sample plagiarized source code pairs) on the top ranked retrieved documents. We report experiments on the SOCO-2014 dataset comprising 12K Java source files with almost 1M lines of code. Our experiments confirm that the AST based approach produces significantly better retrieval effectiveness than a standard BoW representation, i.e., the AST based approach is able to identify a higher number of plagiarized source code documents at top ranks in response to a query source code document. The supervised classifier, trained on features extracted from sample plagiarized source code pairs, is shown to effectively filter and thus further improve the ranked list of retrieved candidate plagiarized documents. 相似文献
15.
Markus Schedl 《Information Retrieval》2012,15(3-4):183-217
Different term weighting techniques such as $TF\cdot IDF$ or BM25 have been used intensely for manifold text-based information retrieval tasks. Their use for modeling term profiles for named entities and subsequent calculation of similarities between these named entities have been studied to a much smaller extent. The recent trend of microblogging made available massive amounts of information about almost every topic around the world. Therefore, microblogs represent a valuable source for text-based named entity modeling. In this paper, we present a systematic and comprehensive evaluation of different term weighting measures, normalization techniques, query schemes, index term sets, and similarity functions for the task of inferring similarities between named entities, based on data extracted from microblog posts. We analyze several thousand combinations of choices for the above mentioned dimensions, which influence the similarity calculation process, and we investigate in which way they impact the quality of the similarity estimates. Evaluation is performed using three real-world data sets: two collections of microblogs related to music artists and one related to movies. For the music collections, we present results of genre classification experiments using as benchmark genre information from allmusic.com . For the movie collection, we present results of multi-class classification experiments using as benchmark categories from IMDb . We show that microblogs can indeed be exploited to model named entity similarity with remarkable accuracy, provided the correct settings for the analyzed aspects are used. We further compare the results to those obtained when using Web pages as data source. 相似文献
16.
Gaurav Pandey Zhaochun Ren Shuaiqiang Wang Jari Veijalainen Maarten de Rijke 《Information Retrieval》2018,21(6):481-506
We address the feature extraction problem for document ranking in information retrieval. We then propose LifeRank, a Linear feature extraction algorithm for Ranking. In LifeRank, we regard each document collection for ranking as a matrix, referred to as the original matrix. We try to optimize a transformation matrix, so that a new matrix (dataset) can be generated as the product of the original matrix and a transformation matrix. The transformation matrix projects high-dimensional document vectors into lower dimensions. Theoretically, there could be very large transformation matrices, each leading to a new generated matrix. In LifeRank, we produce a transformation matrix so that the generated new matrix can match the learning to rank problem. Extensive experiments on benchmark datasets show the performance gains of LifeRank in comparison with state-of-the-art feature selection algorithms. 相似文献
17.
In 2004, the Scottish Parliament commissioned an independent review of abuse in children’s residential establishments between 1950 and 1995. In 2007, the review’s findings were published in a report entitled Historical Abuse Systemic Review: Residential Schools and Children’s Homes in Scotland 1950 to 1995, also known as the Shaw Report. In this article, the Shaw Report provides the jumping off point for a case study of the social justice impact of records. Drawing on secondary literature, interviews, and care-related records, the study identifies narratives that speak to the social justice impact of care records on care-leavers seeking access to them; it also assesses the potential of the surviving administrative records to serve as a foundation on which to construct historical narratives that speak more generally to the experience of children in residential care. 相似文献
18.
This paper explores the performance of top k document retrieval with score-at-a-time query evaluation on impact-ordered indexes in main memory. To better understand execution efficiency in the context of modern processor architectures, we examine the role of index compression on query evaluation latency. Experiments include compressing postings with variable byte encoding, Simple-8b, variants of the QMX compression scheme, as well as a condition that is less often considered—no compression. Across four web test collections, we find that the highest query evaluation speed is achieved by simply leaving the postings lists uncompressed, although the performance advantage over a state-of-the-art compression scheme is relatively small and the index is considerably larger. We explain this finding in terms of the design of modern processor architectures: Index segments with high impact scores are usually short and inherently benefit from cache locality. Index segments with lower impact scores may be quite long, but modern architectures have sufficient memory bandwidth (coupled with prefetching) to “keep up” with the processor. Our results highlight the importance of “architecture affinity” when designing high-performance search engines. 相似文献
19.
T. N. Domnina 《Scientific and Technical Information Processing》2016,43(4):241-250
The megajournal is a new form of an academic open-access journal that is peer reviewed for scientific and methodological soundness. Thus, the perceived importance is not assessed, leaving it to the readers to decide whether an article is of interest and importance to them. After the highly successful launch of the PLOS ONE megajournal, other publishers followed this path. The current paper undertakes a review of the articles published internationally on the megajournal criteria defining its concept. It also traces how the new type of scientific publication has been developing and expanding since the PLoS ONE launch in 2006. 相似文献
20.
Richard J. Matthews 《Archival Science》2016,16(3):213-260
Hägglund’s “radical atheism”—innovative thinking within the philosophical current of “speculative materialism”—revitalizes deconstruction and provides an important basis to define parameters for the archivist’s role as activist for social justice. This paper argues postmodern archival theory gets deconstruction wrong by misreading Derrida’s “Archive fever” as a theory of “archontic power”; this misleads archivists on the call for justice. Properly understanding that justice is undecidable, radical atheism explodes the tension between postmodernists’ appreciation of all views and perspectives and their commitment to right unjust relations of power. This paper first advances the negative argument that “Archive fever” is not about power and injustice. It then advances the positive argument that “Archive fever” is Derrida’s effort to look at actual archives to resolve Freud’s problematic theorizing of a “death drive.” In a close and comprehensive reading of “Archive fever,” this paper explores the notion of “archive fever” as a death drive and suggests Derrida’s efforts are inconclusive. Viewed through the lens of radical atheism, the archive’s “traces”—the material of actual archives writ large in the manner of Derrida’s thinking about a universal archive—serve to mark the flow of time. Understanding the structure of the trace reveals the source of internal contradictions, discontinuities, and instabilities in the meaning of all things. It explains why justice is undecidable. In face of the unconditional condition of this undecidability, we as archivists and humans are compelled to make decisions and to act. Deconstruction politicizes our actions and evokes a responsibility that cannot be absolved. 相似文献