SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH

Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the trainin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Joty, Shafiq Rayhan, Gotmare, Akhilesh Deepak, Li, Junnan, Hoi, Chu Hong
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the training corpus are extracted and used as hard negatives in an online manner during training while keeping the minibatch construction random.