Irrelevant Queries Research Articles

Consistent Weighted Correlation-Based Attention for Transformer Tracking

Attention mechanism takes a crucial role among the key technologies in transformer-based visual tracking. However, the current methods for attention computing neglect the correlation between the query and the key, which results in erroneous correlations. To address this issue, a CWCTrack framework is proposed in this study for transformer visual tracking. To balance the weights of the attention module and enhance the feature extraction of the search region and template region, a consistent weighted correlation (CWC) module is introduced into the cross-attention block. The CWC module computes the correlation score between each query and all keys. Then, the correlation multiplies the consistent weights of the other query–key pairs to acquire the final attention weights. The weights of consistency are computed by the relevance of the query–key pairs. The correlation is enhanced for the relevant query–key pair and suppressed for the irrelevant query–key pair. Experimental results conducted on four prevalent benchmarks demonstrate that the proposed CWCTrack yields preferable performances.

Enabling Privacy-Preserving and Efficient Authenticated Graph Queries on Blockchain-Assisted Clouds

Prior research has introduced a new scenario of blockchain-assisted clouds where the data owner outsources original data to cloud servers and stores some metadata on the blockchain. Despite some research on key-value query and range query in this hybrid-storage scenario, other more complicated data types are not yet supported. In this paper, we conduct pioneering research on authenticated queries for graph data, which is a popular data type such as the knowledge graph data, on the blockchain-assisted cloud. The primary challenge is how to design an authenticated data structure (ADS) that supports authenticated queries and can be easily maintained by the blockchain. To this end, we propose a novel ADS, named PAGB, based on the RSA accumulator and completeness set. It can also prevent the original data from being revealed to the public through blockchain or irrelevant queries. We further optimize our design to be more efficient in terms of communication and computation. The effectiveness and efficiency of PAGB are verified through theoretical analysis and extensive experiments.

Modeling Queries with Contextual Snippets for Information Retrieval

Query expansion under the pseudo-relevance feedback (PRF) framework has been extensively studied in information retrieval. However, most expansion methods are mainly based on the statistics of single terms, which can generate plenty of irrelevant query terms and decrease retrieval performance. To alleviate this problem, we propose an approach that adapts the PRF-based contextual snippets into a context-aware topic model to enhance query representations. Specifically, instead of selecting a series of independent terms, we make full use of the query contextual information and focus on the snippets with the length of n in the PRF documents. Furthermore, we propose a context-aware topic (CAT) model to mine the topic distributions of the query-relevant snippets, namely, fine contextual snippets. In contrast to the traditional topic models that infer the topics from the whole corpus, we establish a bridge between the snippets and the corresponding PRF documents, which can be used for modeling the topics more precisely and efficiently. Finally, the topic distributions of the fine snippets are used for context-aware and topic-sensitive query representations. To evaluate the performance of our approach, we integrate the obtained queries into a topic-based hybrid retrieval model and conduct extensive experiments on various TREC collections. The experimental results show that our query-modeling approach is more effective in boosting retrieval performance compared with the state-of-the-art methods.

Lean Marketing: Know who not to advertise to!

Internet users search the web for more and more relevant information, such as where to find the best online deals, where to go for vacation, what to wear to a wedding, and many others. Online search advertisers target these users based on their search queries. Targeting the right set of users is important as each user clicking on an online search ad costs money to the advertiser. Savvy advertisers usually pick keywords that are niche and “non-intuitive” because such keywords are cheaper than more popular keywords due to lesser number of advertisers competing for them. In order to find such keywords, multiple information sources such as web ontologies open to the public, search engine results, and search query logs were mined in the past. In these studies, the universe of all relevant keywords was approximated as the relevant keywords of all techniques combined. A given keyword selection technique was then evaluated based on the relevance of the keywords it selected to the target page that is to be advertised. Since the universe of relevant keywords was approximate, it had implications for advertising efficiency. For the campaign dataset we used in this study, out of a total of $75K spent on the campaign, 10% of this total budget was spent on the irrelevant queries. Our primary goal in this work is to reduce this excess budget spent on the irrelevant queries. For this purpose, we learn the characteristics of the “irrelevant” queries using the campaign’s past performance data. Words and phrases that occur frequently in queries, which are not likely to convert, are used as a proxy to decide who not to advertise to. In this way, we plan to preserve more of the marketing budget for queries that are more likely to convert. In our empirical study, we used a logistic regressor for identifying negative words, which distinguished the non-converting queries from the converting ones, and pruned the non-converting queries using the negatives identified. Our approach decreased the average customer acquisition cost of a live search campaign by 25% and cut the overall campaign spend by 28.6%.

La recherche collaborative d'information sur Internet : impact de l'affinité entre les jeunes collaborateurs

Two experimental studies aim at describing the impacts of pair interaction and affective factors during the process of collaborative search for information on the World Wide Web when end-users are young learners recruited from Grade 3. In three successive sessions, students were asked to find answers to questions related to medieval history on the Internet. In these three sessions, students were asked to find these answers alone (condition "Alone"), or with a friend (condition "Affinity +"), or with another pupil who was not a friend (condition "Affinity -"). Several significant results have been obtained: (1) pairs retrieved effectively more answers, more correct answers, and were more efficient than singles; (2) pairs composed of children without social affinity retrieved more answers, more correct answers and were more efficient than pairs composed of friends; (3) pairs composed of friends produced significantly more irrelevant queries than pairs composed of children without social affinity; (4) pairs composed of children without social affinity are engaged in a great deal of consensus seeking, compared with the pairs composed of friends.

The impact of friendship on synchronous collaborative retrieval tasks in the primary school

AbstractTwo experiments aim at describing the impact of friendship during a synchronous collaborative information retrieval (SCIR) with young pupils (recruited in Grade 3). In the first study, 68 pupils were asked to look for 13 answers in one of the three following conditions: on an individual basis (condition “Single”), as part of a designed duo with social friendship (condition “Affinity +”), or as part of a designed duo without social friendship (condition “Affinity −”). In the second experiment, we investigated more precisely the impact of friendship on verbal interactions between partners. Main results obtained in these two experiments are the following: (1) pairs retrieved effectively more answers, more correct answers and were more efficient than singles; (2) pairs composed of pupils without social friendship retrieved more answers, more correct answers and were more efficient than pairs composed by friends; (3) pairs composed of friends produced significantly more irrelevant queries; and (4) pairs composed of friends produced more verbalisations related to conflicts, while pairs composed of pupils without social friendship are engaged in a great deal of consensus seeking. Finally, educational implications are discussed.

Ontology-supported FAQ processing and ranking techniques

This paper describes an FAQ system on the Personal Computer (PC) domain, which employs ontology as the key technique to pre-process FAQs and process user query. It is also equipped with an enhanced ranking technique to present retrieved, query-relevant results. Basically, the system bases on the wrapper technique to help clean, retrieve, and transform FAQ information collected from a heterogeneous environment and stores it in an ontological database. During retrieval of FAQs, the system trims irrelevant query keywords, employs either full keywords match or partial keywords match to retrieve FAQs, and removes conflicting FAQs before turning the final results to the user. Ontology plays the key role in all the above activities. To produce a more effective presentation of the search results, the system employs an enhanced ranking technique, which includes Appearance Probability, Satisfaction Value, Compatibility Value, and Statistic Similarity Value as four measures properly weighted to rank the FAQs. Our experiments show the system does improve precision rate and produces better ranking results. The proposed FAQ system manifests the following interesting features. First, the ontology-supported FAQ extraction from webpages can clean FAQ information by removing redundant data, restore missing data, and resolve inconsistent data. Second, the FAQs are stored in an ontology-directed internal format, which supports semantics-constrained retrieval of FAQs. Third, the ontology-supported natural language processing of user query helps pinpoint user's intent. Finally, the partial keywords match-based ranking method helps present user-most-wanted, conflict-free FAQ solutions for the user.

Interruption and Reorientation Effects of a Situation Awareness Probe on Driving Hazard Anticipation

A driving-based Hazard Perception Test of anticipation (HPT) was applied alongside an interruption-based Situation Awareness (SA) probe to investigate the effects of interruption and reorienting the operator to the task. Content of the SA probe was manipulated in four conditions: No queries, SA queries, orienting queries, and irrelevant queries. The findings were firstly that the HPT scores correlated with the SA probe scores in the SA queries condition. Secondly, there was a negative effect of interruption on HPT scores. Finally, HPT scores increased during SA queries and orienting queries but not during irrelevant queries. The results imply that previous research showing no interruption effects from SA probe methods may be due to the orienting effects of the queries compensating for a decrease in scores caused by interruption.