Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data 2013
DOI: 10.1145/2463676.2465280
|View full text |Cite
|
Sign up to set email alerts
|

Leveraging transitive relations for crowdsourced joins

Abstract: The development of crowdsourced query processing systems has recently attracted a significant attention in the database community. A variety of crowdsourced queries have been investigated. In this paper, we focus on the crowdsourced join query which aims to utilize humans to find all pairs of matching objects from two collections. As a human-only solution is expensive, we adopt a hybrid human-machine approach which first uses machines to generate a candidate set of matching pairs, and then asks humans to label… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
194
0

Year Published

2014
2014
2021
2021

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 188 publications
(195 citation statements)
references
References 24 publications
1
194
0
Order By: Relevance
“…While crowdsourcing has been present in both the research community (e.g., [25]) and industry (e.g., oDesk and Amazon Mechanical Turk), spatial crowdsourcing only recently received attention (e.g., [21], [15] and [14]). (k) ANW , Yelp-Linear…”
Section: Related Workmentioning
confidence: 99%
“…While crowdsourcing has been present in both the research community (e.g., [25]) and industry (e.g., oDesk and Amazon Mechanical Turk), spatial crowdsourcing only recently received attention (e.g., [21], [15] and [14]). (k) ANW , Yelp-Linear…”
Section: Related Workmentioning
confidence: 99%
“…If our database contains n records we may need to ask O(n 2 ) pairwise questions for ER. In general, we can exploit the transitive nature of the equality relation to reduce the number of questions we ask the crowd [16]. For example, consider the Stanford example described above.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, Wang et al [16] posited that the strategy of asking questions in decreasing order of pairwise probability is the optimal strategy for this problem. However, we show in this paper that the claim is not correct.…”
Section: Introductionmentioning
confidence: 99%
“…Crowdsourced joins have been mainly defined in terms of entity resolution, where joining two datasets means finding all pairs of tuples that refer to the same entity [4,5]. Conversely, Jim can handle arbitrary n-ary join predicates, thus targeting a quite different and more intricate goal for the crowd i.e., inferring such join predicates from a set of positive and negative labels.…”
Section: Introductionmentioning
confidence: 99%
“…As a further difference, the existing systems that allow join processing with the crowd [4,5] do not take into account the labels already given by the user to adjust the order of presenting new tuples for labeling. On the other hand, Jim continuously interleaves the user's feedback and the inference process.…”
Section: Introductionmentioning
confidence: 99%