Show simple item record

dc.contributor.authorAgarwal, Aman
dc.date.accessioned2020-08-10T20:23:38Z
dc.date.available2020-08-10T20:23:38Z
dc.date.issued2020-05
dc.identifier.otherAgarwal_cornellgrad_0058F_12009
dc.identifier.otherhttp://dissertations.umi.com/cornellgrad:12009
dc.identifier.urihttps://hdl.handle.net/1813/70359
dc.description102 pages
dc.description.abstractLearning-to-rank (LTR) search results in large scale industrial information retrieval settings, such as personal email and e-commerce, directly from logged implicit user feedback such as clicks is highly attractive since such feedback is ubiquitous, routinely collected, user-focused and time-sensitive unlike manual relevance annotations or slow, disruptive A/B testing protocols. However, LTR from such feedback is challenging since it can be very partial and biased as signals of relevance. In particular, position bias must be addressed since higher ranks are more likely to be examined and clicked, and thus naively interpreting clicks as relevance labels leads to undesirable feedback loops and sub-optimal ranking quality. Towards this end, we develop a theoretical framework based on counterfactual reasoning that systematically deals with the various forms of position bias inherent in user behavior, and demonstrate its effectiveness in several real-world settings including Gmail and Arxiv search. While the framework can be adapted for any form of implicit feedback, we primarily focus on click data since they are routinely logged and reliable indicators of user intent. We present our key contributions within this framework, especially Intervention Harvesting, the first method for consistent position-bias estimation without additional online interventions or relevance modeling using logs from multiple rankers. The general unbiased LTR framework, and addressing position-dependent trust bias in relevance evaluation (in addition to examination bias) are also described in detail.
dc.titleUnbiased Learning-to-Rank from Logged Implicit Feedback
dc.typedissertation or thesis
thesis.degree.disciplineComputer Science
thesis.degree.grantorCornell University
thesis.degree.levelDoctor of Philosophy
thesis.degree.namePh. D., Computer Science
dc.contributor.chairJoachims, Thorsten
dc.contributor.committeeMemberWilson, Andrew
dc.contributor.committeeMemberSridharan, Karthik
dcterms.licensehttps://hdl.handle.net/1813/59810
dc.identifier.doihttps://doi.org/10.7298/y0vq-2437


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Statistics