HPTA: High-Performance Text Analytics

Hans Vandierendonck; Karen Murphy; Mahwish Arif; Dimitrios S. Nikolopoulos

doi:10.1109/BigData.2016.7840632

HPTA: High-Performance Text Analytics

Hans Vandierendonck, Karen Murphy, Mahwish Arif, Dimitrios S. Nikolopoulos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

494 Downloads (Pure)

Abstract

One of the main targets of data analytics is unstructured data, which primarily involves textual data. High-performance processing of textual data is non-trivial. We present the HPTA library for high-performance text analytics. The library helps programmers to map textual data to a dense numeric representation, which can be handled more efficiently. HPTA encapsulates three performance optimizations: (i) efficient memory management for textual data, (ii) parallel computation on associative data structures that map text to values and (iii) optimization of the type of associative data structure depending on the program context. We demonstrate that HPTA outperforms popular frameworks for text analytics such as scikit-learn and Spark.

Original language	English
Title of host publication	Proceedings of tge IEEE International Conference on Big Data
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	416-423
Number of pages	8
DOIs	https://doi.org/10.1109/BigData.2016.7840632
Publication status	Published - 06 Feb 2017
Event	2016 IEEE International Conference on Big Data - DC, Washington, United States Duration: 05 Dec 2016 → 08 Dec 2016

Conference

Conference	2016 IEEE International Conference on Big Data
Country/Territory	United States
City	Washington
Period	05/12/2016 → 08/12/2016

Keywords

data analytics
performance optimization
text analytics

Access to Document

10.1109/BigData.2016.7840632Licence: Unspecified

HPTA: A Library for High-Performance Text Analytics
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 814 KBLicence: Unspecified

R1451CSC: Hybrid Static/Dynamic Scheduling for Task Dataflow Parallel Programs
Vandierendonck, H. (PI)
28/07/2014 → 02/03/2017
Project: Research
R6438CSC: An Adaptive, highly Scalable Analytics Platform
Vandierendonck, H. (PI), Nikolopoulos, D. (CoI) & Robinson, P. (CoI)
21/03/2014 → 28/02/2017
Project: Research

Hans Vandierendonck
- h.vandierendonckqub.acuk
Person: Academic

Cite this

@inproceedings{9d6fbd2e187e46b8b78a0a114f5d8ac7,

title = "HPTA: High-Performance Text Analytics",

abstract = "One of the main targets of data analytics is unstructured data, which primarily involves textual data. High-performance processing of textual data is non-trivial. We present the HPTA library for high-performance text analytics. The library helps programmers to map textual data to a dense numeric representation, which can be handled more efficiently. HPTA encapsulates three performance optimizations: (i) efficient memory management for textual data, (ii) parallel computation on associative data structures that map text to values and (iii) optimization of the type of associative data structure depending on the program context. We demonstrate that HPTA outperforms popular frameworks for text analytics such as scikit-learn and Spark. ",

keywords = "data analytics, performance optimization, text analytics",

author = "Hans Vandierendonck and Karen Murphy and Mahwish Arif and Nikolopoulos, {Dimitrios S.}",

year = "2017",

month = feb,

day = "6",

doi = "10.1109/BigData.2016.7840632",

language = "English",

pages = "416--423",

booktitle = "Proceedings of tge IEEE International Conference on Big Data",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2016 IEEE International Conference on Big Data ; Conference date: 05-12-2016 Through 08-12-2016",

}

TY - GEN

T1 - HPTA: High-Performance Text Analytics

AU - Vandierendonck, Hans

AU - Murphy, Karen

AU - Arif, Mahwish

AU - Nikolopoulos, Dimitrios S.

PY - 2017/2/6

Y1 - 2017/2/6

N2 - One of the main targets of data analytics is unstructured data, which primarily involves textual data. High-performance processing of textual data is non-trivial. We present the HPTA library for high-performance text analytics. The library helps programmers to map textual data to a dense numeric representation, which can be handled more efficiently. HPTA encapsulates three performance optimizations: (i) efficient memory management for textual data, (ii) parallel computation on associative data structures that map text to values and (iii) optimization of the type of associative data structure depending on the program context. We demonstrate that HPTA outperforms popular frameworks for text analytics such as scikit-learn and Spark.

AB - One of the main targets of data analytics is unstructured data, which primarily involves textual data. High-performance processing of textual data is non-trivial. We present the HPTA library for high-performance text analytics. The library helps programmers to map textual data to a dense numeric representation, which can be handled more efficiently. HPTA encapsulates three performance optimizations: (i) efficient memory management for textual data, (ii) parallel computation on associative data structures that map text to values and (iii) optimization of the type of associative data structure depending on the program context. We demonstrate that HPTA outperforms popular frameworks for text analytics such as scikit-learn and Spark.

KW - data analytics

KW - performance optimization

KW - text analytics

U2 - 10.1109/BigData.2016.7840632

DO - 10.1109/BigData.2016.7840632

M3 - Conference contribution

SP - 416

EP - 423

BT - Proceedings of tge IEEE International Conference on Big Data

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Conference on Big Data

Y2 - 5 December 2016 through 8 December 2016

ER -

HPTA: High-Performance Text Analytics

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

R1451CSC: Hybrid Static/Dynamic Scheduling for Task Dataflow Parallel Programs

R6438CSC: An Adaptive, highly Scalable Analytics Platform

Profiles

Hans Vandierendonck

Cite this