English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic crash bucketing is a crucial phase in the software developmentprocess for efficiently triaging bug reports. It generally consists in groupingsimilar reports through clustering techniques. However, with real-timestreaming bug collection, systems are needed to quickly answer the question:What are the most similar bugs to a new one?, that is, efficiently findnear-duplicates. It is thus natural to consider nearest neighbors search totackle this problem and especially the well-known locality-sensitive hashing(LSH) to deal with large datasets due to its sublinear performance andtheoretical guarantees on the similarity search accuracy. Surprisingly, LSH hasnot been considered in the crash bucketing literature. It is indeed not trivialto derive hash functions that satisfy the so-called locality-sensitive propertyfor the most advanced crash bucketing metrics. Consequently, we study in thispaper how to leverage LSH for this task. To be able to consider the mostrelevant metrics used in the literature, we introduce DeepLSH, a Siamese DNNarchitecture with an original loss function, that perfectly approximates thelocality-sensitivity property even for Jaccard and Cosine metrics for whichexact LSH solutions exist. We support this claim with a series of experimentson an original dataset, which we make available.

DeepLSH: Deep Locality-Sensitive Hash Learning for Fast and Efficient Near-Duplicate Crash Report Detection