High Performance Computing for Understanding Natural Language

The amount of user-generated text available online is growing at an ever-increasing rate due to tremendous progress in enlarging inexpensive storage capacity, processing capabilities, and the popularity of online outlets and social networks. Learning language representation and solving tasks in an end-to-end manner, without a need for human-expert feature extraction and creation, has made models more accurate and much more complicated in the number of parameters, requiring parallelized and distributed resources high-performance computing or cloud. This chapter gives an overview of state-of-the-art natural language processing problems, algorithms, models, and libraries. Parallelized and distributed ways to solve text understanding, representation, and classification tasks are also discussed. Additionally, the importance of high-performance computing for natural language processing applications is illustrated by showing details of a few specific applications that use pre-training or self-supervised learning on large amounts of data in text understanding.

Download Full-text

Report on workshop on high performance computing and communications for grand challenge applications: computer vision, speech and natural language processing, and artificial intelligence

IEEE Transactions on Knowledge and Data Engineering ◽

10.1109/69.204098 ◽

1993 ◽

Vol 5 (1) ◽

pp. 138-154 ◽

Cited By ~ 13

Author(s):

B.W. Wah ◽

T.S. Huang ◽

A.K. Joshi ◽

D. Moldovan ◽

J. Aloimonos ◽

...

Keyword(s):

Artificial Intelligence ◽

Computer Vision ◽

Natural Language Processing ◽

Natural Language ◽

High Performance Computing ◽

Language Processing ◽

High Performance ◽

Grand Challenge ◽

Performance Computing

Download Full-text

CLAMP – a toolkit for efficiently building customized clinical natural language processing pipelines

Journal of the American Medical Informatics Association ◽

10.1093/jamia/ocx132 ◽

2017 ◽

Vol 25 (3) ◽

pp. 331-336 ◽

Cited By ~ 64

Author(s):

Ergin Soysal ◽

Jingqi Wang ◽

Min Jiang ◽

Yonghui Wu ◽

Serguei Pakhomov ◽

...

Keyword(s):

Natural Language Processing ◽

User Interface ◽

Natural Language ◽

Language Processing ◽

High Performance ◽

Smoking Status ◽

Entity Recognition ◽

Graphic User Interface ◽

Clinical Text ◽

Clinical Natural Language Processing

Abstract Existing general clinical natural language processing (NLP) systems such as MetaMap and Clinical Text Analysis and Knowledge Extraction System have been successfully applied to information extraction from clinical text. However, end users often have to customize existing systems for their individual tasks, which can require substantial NLP skills. Here we present CLAMP (Clinical Language Annotation, Modeling, and Processing), a newly developed clinical NLP toolkit that provides not only state-of-the-art NLP components, but also a user-friendly graphic user interface that can help users quickly build customized NLP pipelines for their individual applications. Our evaluation shows that the CLAMP default pipeline achieved good performance on named entity recognition and concept encoding. We also demonstrate the efficiency of the CLAMP graphic user interface in building customized, high-performance NLP pipelines with 2 use cases, extracting smoking status and lab test values. CLAMP is publicly available for research use, and we believe it is a unique asset for the clinical NLP community.

Download Full-text

High Performance Natural Language Processing

10.18653/v1/2020.emnlp-tutorials.4 ◽

2020 ◽

Author(s):

Gabriel Ilharco ◽

Cesar Ilharco ◽

Iulia Turc ◽

Tim Dettmers ◽

Felipe Ferreira ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

High Performance

Download Full-text

APLIKASI AGEN CERDAS UNTUK PEMBELAJARAN PEMPROGRAMAN BERORIENTASI OBJEK BERBASIS NATURAL LANGUAGE PROCESSING (NLP)

10.31227/osf.io/3jth2 ◽

2018 ◽

Author(s):

Khairil Anam ◽

SEHMAN

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

High Performance ◽

Object Oriented Programming ◽

Learning System ◽

Computer Laboratory ◽

Final Project ◽

Laboratory Learning ◽

The Creation

The existence of a touch of technology on laboratory learning becomes another alternative as a supporter of laboratory learning. Different practitioner's wishes and intensity of relatively short laboratory practice which resulted in dissatisfaction in the implementation of a practicum. Thus, an intelligent learning alternative is needed. This intelligent learning aims to provide high-quality and high-performance training skills that can assist the practitioner in solving problems related to practicum materials. The intelligent learning system is a learning system that handles some student instruction without any intervention from a teacher.Alternative learning system that can support the creation of Intelligent Learning System is by Natural Language Processing (NLP) method. This final project provides an explanation of the creation and implementation of intelligent learning systems in the Object Oriented Programming Computer Laboratory. This system consists of several stages: parsing, similarity, stemming, Knowledge Base which is designed in an interactive form between praktikan and agent based dialoge based application. The success rate of this system in answering questions from praktikan session II is 88.75%.

Download Full-text

The architectures analyzing for computational workflows designing in a distributed environment

Bulletin of V.N. Karazin Kharkiv National University, series «Mathematical modeling. Information technology. Automated control systems» ◽

10.26565/2304-6201-2020-46-01 ◽

2020 ◽

Keyword(s):

Cloud Computing ◽

High Performance Computing ◽

High Performance ◽

Business Processes ◽

Service Oriented Architecture ◽

Distributed Environment ◽

End User ◽

Distributed Resources ◽

Computing Architecture ◽

Performance Computing

The paper presents a model of computational workflows based on end-user understanding and provides an overview of various computational architectures, such as computing cluster, Grid, Cloud Computing, and SOA, for building workflows in a distributed environment. A comparative analysis of the capabilities of the architectures for the implementation of computational workflows have been shown that the workflows should be implemented based on SOA, since it meets all the requirements for the basic infrastructure and provides a high degree of compute nodes distribution, as well as their migration and integration with other systems in a heterogeneous environment. The Cloud Computing architecture using may be efficient when building a basic information infrastructure for the organization of distributed high-performance computing, since it supports the general and coordinated usage of dynamically allocated distributed resources, allows in geographically dispersed data centers to create and virtualize high-performance computing systems that are able to independently support the necessary QoS level and, if necessary, to use the Software as a Service (SaaS) model for end-users. The advantages of the Cloud Computing architecture do not allow the end user to realize business processes design automatically, designing them "on the fly". At the same time, there is the obvious need to create semantically oriented computing workflows based on a service-oriented architecture using a microservices approach, ontologies and metadata structures, which will allow to create workflows “on the fly” in accordance with the current request requirements.

Download Full-text