Identification of topics in source code

Girish Maskeri  Rama; Kenneth Heafield; Santonu Sarkar

Identification of topics in source code

Girish Maskeri Rama (Inventor), Kenneth Heafield (Inventor), Santonu Sarkar (Inventor)

Research output: Patent

Abstract

Topics in source code can be identified using Latent Dirichlet Allocation (LDA) by receiving source code, identifying domain specific keywords from the source code, generating a keyword matrix, processing the keyword matrix and the source code using LDA, and outputting a list of topics. The list of topics is output as collections of domain specific keywords. Probabilities of domain specific keywords belonging to their respective topics can also be output. The keyword matrix comprises weighted sums of occurrences of domain specific keywords in the source code.

Original language	English
Patent number	US8209665 B2
Priority date	8/04/08
Publication status	Published - 26 Jun 2012

Access to Document

US8209665Accepted author manuscript, 116 KB

http://www.google.com/patents/US8209665

Cite this

@misc{caf922820dae4f64903dcdc3d14be5c8,

title = "Identification of topics in source code",

abstract = "Topics in source code can be identified using Latent Dirichlet Allocation (LDA) by receiving source code, identifying domain specific keywords from the source code, generating a keyword matrix, processing the keyword matrix and the source code using LDA, and outputting a list of topics. The list of topics is output as collections of domain specific keywords. Probabilities of domain specific keywords belonging to their respective topics can also be output. The keyword matrix comprises weighted sums of occurrences of domain specific keywords in the source code.",

author = "Rama, {Girish Maskeri} and Kenneth Heafield and Santonu Sarkar",

year = "2012",

month = jun,

day = "26",

language = "English",

type = "Patent",

note = "US8209665 B2",

}

TY - PAT

T1 - Identification of topics in source code

AU - Rama, Girish Maskeri

AU - Heafield, Kenneth

AU - Sarkar, Santonu

PY - 2012/6/26

Y1 - 2012/6/26

N2 - Topics in source code can be identified using Latent Dirichlet Allocation (LDA) by receiving source code, identifying domain specific keywords from the source code, generating a keyword matrix, processing the keyword matrix and the source code using LDA, and outputting a list of topics. The list of topics is output as collections of domain specific keywords. Probabilities of domain specific keywords belonging to their respective topics can also be output. The keyword matrix comprises weighted sums of occurrences of domain specific keywords in the source code.

AB - Topics in source code can be identified using Latent Dirichlet Allocation (LDA) by receiving source code, identifying domain specific keywords from the source code, generating a keyword matrix, processing the keyword matrix and the source code using LDA, and outputting a list of topics. The list of topics is output as collections of domain specific keywords. Probabilities of domain specific keywords belonging to their respective topics can also be output. The keyword matrix comprises weighted sums of occurrences of domain specific keywords in the source code.

M3 - Patent

M1 - US8209665 B2

ER -

Identification of topics in source code

Abstract

Access to Document

Fingerprint

Cite this