A5100709758- Natural Language Processing Techniques
- Topic Modeling
- Semantic Web and Ontologies
- International Maritime Law Issues
- Global Political and Economic Relations
- SMEs Development and Digital Marketing
- Coastal Management and Development
- Speech and dialogue systems
- Artificial Intelligence in Games
- Global trade and economics
- Image Retrieval and Classification Techniques
- Humor Studies and Applications
- Asian Geopolitics and Ethnography
- Advanced Image and Video Retrieval Techniques
- Community-based Tourism Development and Sustainability
- Legal Studies and Policies
- Korean Peninsula Historical and Political Studies
- Advanced Text Analysis Techniques
- Consumer Behavior and Marketing Influence
- Language, Metaphor, and Cognition
- Marine and Coastal Ecosystems
- European Politics and Security
- Edcuational Technology Systems
- Arctic and Russian Policy Studies
- Plant Growth and Agriculture Techniques
State University of Medan
2015-2024
Padjadjaran University
2014-2023
Mulawarman University
2016-2023
Universitas Sahid Jakarta
2023
Universitas Sisingamangaraja XII Tapanuli
2018-2021
University of North Sumatra
2021
President University
2012-2020
School of International Relations
2012-2020
Universitas Sisingamangaraja XII
2020
University of International Relations
2017-2020
Daniel Zeman, Martin Popel, Milan Straka, Jan Hajič, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Potthast, Francis Tyers, Elena Badmaeva, Memduh Gokirmak, Anna Nedoluzhko, Silvie Cinková, Hajič jr., Jaroslava Hlaváčová, Václava Kettnerová, Zdeňka Urešová, Jenna Kanerva, Stina Ojala, Missilä, Christopher D. Manning, Sebastian Schuster, Siva Reddy, Dima Taji, Nizar Habash, Herman Leung, Marie-Catherine de Marneffe, Manuela Sanguinetti, Maria Simi, Hiroshi...
This article presents a series of experiments in automatically generating poetic texts. We confined our attention to the generation texts which are syntactically well-formed, meet certain pre-specified patterns metre and broadly convey some given meaning. Such aspects can be formally defined, thus avoiding complications imagery interpretation that central assessing more free forms verse. Our implemented system, McGONAGALL, applies genetic algorithm construct such It uses sophisticated...
We describe our work on designing a linguistically principled part of speech (POS) tagset for the Indonesian language. The process involves detailed study and analysis existing tagsets manual tagging an corpus. results this are POS consisting 23 tags corpus over 250.000 lexical tokens that have been manually tagged using tagset.
Batik is a traditional clothwith unique patterns applied to fabric using wax-resist dyeing technique. Aside from preserving this rich cultural heritage, the automated recognition of would enable many interesting applications. This paper introduces an approach batik pattern Scale Invariant Feature Transform (SIFT) as feature extraction method. The challenging issues that arise are due highly symmetrical and repetitive properties patterns. Hough transform, evidence-based method object...
In an effort to focus on tractable problems, computational natural language understanding systems have typically addressed phenomena that are amenable combinatorial approaches using static and stereotypical semantic representations. Although such adequate for much of language, they're not easily extended capture humans' more creative interpretation capacities. This paper proposes a model humor comprehension based frame-shifting within simulation-based natural-language-understanding system.
This paper describes work on a part-of-speech tagger for the Indonesian language by employing rule-based approach. The system tokenizes documents while also considering multi-word expressions and recognizes named entities. It then applies tags to every token, starting from closed-class words open-class disambiguates based set of manually defined rules. currently obtains an accuracy 79% tagged corpus roughly 250.000 tokens.
Since the early 1990s, there have been a number of small-scale computer programs that automatically constructed simple verbal jokes (puns), but none these were fully developed systems could be used for practical application. We describe building and testing STANDUP program – large-scale, robust, interactive, user-friendly pun-generator (inspired by Binsted's JAPE program), which is aimed at allowing children, particularly those with communication disabilities, to develop their linguistic...
The interactive STANDUP software was developed to provide children who use augmentative and alternative communication (AAC) with a “language playground.” provides appropriate functionality for users physical, speech, language impairments generate tell novel punning riddles at different levels of complexity. evaluated nine cerebral palsy during an eight-week study. Results show that the participants were able jokes minimal or no support. impacted favorably on general AAC use. study results...
Scene classification based on latent Dirichlet allocation (LDA) is a more general modeling method known as bag of visual words, in which the construction vocabulary crucial quantization process to ensure success classification. A framework developed using following new aspects: Gaussian mixture clustering for process, use an integrated (IVV), built union all centroids obtained from separate each class, and usage some features, including edge orientation histogram, CIELab color moments,...
<p>This paper systematically investigates the effect of image texture features on batik motif retrieval performance. The process uses a query to find matching images in database. In this study, feature fusion various such as Gabor, Log-Gabor, Grey Level Co-Occurrence Matrices (GLCM), and Local Binary Pattern (LBP) are attempted retrieval. With regards performance evaluation, both individual fused sets applied. Experimental results show that optimal outperforms Among tested, Log-Gabor...
This study aims to discuss Indonesia implemented strategy in optimizing effort strengthening and enhance collaboratively get investment. In fact, Indonesia's economic growth 2020 had experienced a contraction due the outbreak of COVID-19 pandemic. At that time, second-quarter decreased gradually recovered third fourth quarters. second quarter 2021, Indonesian hit around seven percent. A thriving financially sound capital market helps supports country's can inter-community cooperation. The...
This study aims to analyze the performance of Palm Oil Cooperative with Balanced Scorecard approach. type research is descriptive quantitative. The data used are primary in form Financial Report North Sumatera. population and samples some Cooperatives Sumatra. Analysis indicators Scorecard. results show that role Perspectives has a significant effect on formation Fresh Fruit Bunch (TBS) Market Price mechanism. While variable Non-Financial no TBS significance variables caused by Regulation as...
This paper describes the development of an Indonesian NER system using online data such as Wikipedia 1 and DBPedia 2. The is based on Stanford [8] utilizes training documents constructed automatically from Wikipedia. Each entity, i.e. word or phrase that has a hyperlink, in are tagged according to information obtained DBPedia. In this very first version, we only interested three entities, namely: Person, Place, Organization. evaluated cross fold validation also gold standard was manually...
Gagasan Poros Maritim Dunia Indonesia harus dibangun lewat konsepsi yang kuat dan implementatif secara ekonomi politik internasional.Konsepsi itu dapat menjadi arah, kaidah pokok paradigma bersama semua pemangku kepentingan untuk memosisikan sebagai negara inti pusat gravitasi kemaritiman dunia. Ada tiga terobosan dilakukan pemerintah, yaitu: Pertama, di level global, mampu dunia karena letak geografisnya strategis dukungan kekayaan sumber daya alam maritim sektor basis, dimana basis...
<p>This paper systematically investigates the effect of image texture features on batik motif retrieval performance. The process uses a query to find matching images in database. In this study, feature fusion various such as Gabor, Log-Gabor, Grey Level Co-Occurrence Matrices (GLCM), and Local Binary Pattern (LBP) are attempted retrieval. With regards performance evaluation, both individual fused sets applied. Experimental results show that optimal outperforms Among tested, Log-Gabor...
Named Entity Recognition (NER) plays a significant role in Information Extraction (IE). In English, the NER systems have achieved excellent performance, but for Indonesian language, still need lot of improvement. To create reliable system using machine learning approach, massive dataset to train classifier is must. Several studies proposed methods automatically building Wikipedia articles as source and DBpedia reference determining entity types automatically. The objective our research...