-
2024Customer behavioral data significantly impacts e-commerce search systems. However, in the case of less common queries, the associated behavioral data tends to be sparse and noisy, offering inadequate support to the search mechanism. To address this challenge, the concept of query reformulation has been introduced. It suggests that less common queries could utilize the behavior patterns of their popular
-
IGARSS 20242024The ever-increasing demand for digital maps in various do-mains amplifies the importance of having accurate and up-to-date maps. To address this, the proposed system pervasively conflates large volume of sign detections recorded by a transportation fleet of vehicles into map database. Detected and geo-localized sign objects collected from the fleet over a time period are passed through a context-aware clustering
-
2024Evaluating a new ranking policy using data logged by a previously deployed policy requires a counterfactual (off-policy) estimator that corrects for presentation and selection biases. Some estimators (e.g., the position-based model) perform this correction by making strong assumptions about user behavior, which can lead to high bias if the assumptions are not met. Other estimators (e.g., the item-position
-
2024Music and media search spell correction is distinct as it involves named entities like artist, album and podcast names, keywords from track titles and catchy phrases from lyrics. Users often mix artist names and keywords from track title or lyrics making spell correction highly contextual. Data drift in search queries caused during calendar event days or a newly released music album, brings a unique challenge
-
ACM Transactions on Recommender Systems2024Offline data-driven evaluation is considered a low-cost and more accessible alternative to the online empirical method of assessing the quality of recommender systems. Despite their popularity and effectiveness, most data-driven approaches are unsuitable for evaluating interactive recommender systems. In this paper, we attempt to address this issue by simulating the user interactions with the system as
Related content
-
May 23, 2020AWS’s Cord-19 Search website allows researchers to easily query tens of thousands of scientific and medical papers on the deadly virus.
-
May 19, 2020At smaller vocabulary sizes, tokenizers trained on unannotated data work best.
-
March 18, 2020Developing machine learning frameworks that can enhance context-aware AI has been an area of focus for Dhillon’s entire career.
-
March 12, 2020Predicting customers’ “contexts of use” could improve online product discovery.
-
March 10, 2020Vanessa Murdock, manager of Applied Science, talks about how her training as a classical pianist helps her be a better scientist, why she joined Amazon, and how her work at Amazon affects the lives of millions of customers.
-
March 10, 2020Crowdsourcing reveals sources of information that could improve product discovery algorithms.