• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.3
• /
• pp.285-307
• /
• 2009

This paper introduces DICE, a Domain-Independent text Classification Engine. DICE is robust, efficient, and domain-independent in terms of software and architecture. Each module of the system is clearly modularized and encapsulated for extensibility. The clear modular architecture allows for simple and continuous verification and facilitates changes in multiple cycles, even after its major development period is complete. Those who want to make use of DICE can easily implement their ideas on this test bed and optimize it for a particular domain by simply adjusting the configuration file. Unlike other publically available tool kits or development environments targeted at general purpose classification models, DICE specializes in text classification with a number of useful functions specific to it. This paper focuses on the ways to locate the optimal states of a practical text classification framework by using various adaptation methods provided by the system such as feature selection, lemmatization, and classification models.

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.290-301
• /
• 2000

Most morphological analysis methods require repetitive procedures of input character code conversion, segmentation and lemmatization of constituent morphemes, filtering of candidate results through looking up lexicons, which causes run-time inefficiency. To alleviate such problem of run-time inefficiency, many systems have introduced the notion of 'pre-analysis' of words. However, this method based on pre-analysis dictionary of surface also has a critical drawback in its practical application because the size of the dictionaries increases indefinite to cover all words. This paper hybridizes both extreme approaches methodologically to overcome the problems of the two, and presents a method of morphological analysis based on pre-analysis of partial words. Under such hybridized scheme, most computational overheads, such as segmentation and lemmatization of morphemes, are shifted to building-up processes of the pre-analysis dictionaries and the run-time dictionary look-ups are greatly reduced, so as to enhance the run-time performance of the system. Moreover, additional computing overheads such as input character code conversion can also be avoided because this method relies upon no graphemic processing.

• Language and Information
• /
• v.6 no.2
• /
• pp.105-128
• /
• 2002

Morphologically annotated corpora are the basis for many tasks of computational linguistics. Most current approaches use statistically driven methods of morphological analysis, that provide just POS-tags. While this is sufficient for some applications, a rule-based full morphological analysis also yielding lemmatization and segmentation is needed for many others. This work thus aims at 〔1〕 introducing a rule-based Korean morphological analyzer called Kormoran based on the principle of linearity that prohibits any combination of left-to-right or right-to-left analysis or backtracking and then at 〔2〕 showing how it on be used as a POS-tagger by adopting an ordinary technique of preprocessing and also by filtering out irrelevant morpho-syntactic information in analyzed feature structures. It is shown that, besides providing a basis for subsequent syntactic or semantic processing, full morphological analyzers like Kormoran have the greater power of resolving ambiguities than simple POS-taggers. The focus of our present analysis is on Korean text.

• Journal of Information Technology Services
• /
• v.17 no.2
• /
• pp.111-128
• /
• 2018

About 3.9 million apps and 24 primary categories can be approved on Apple iTunes Store. Making accurate categorization can potentially receive many benefits for developers, app stores, and users, such as improving discoverability and receiving long-term revenue. However, current categorization problems may cause usage inefficiency and confusion, especially for cross-attribution, etc. This study focused on evaluating the reliability of app categorization on Apple iTunes Store by using several rounds of inter-rater reliability statistics, locating categorization problems based on Machine Learning, and making more accurate suggestions about representative functionality stems for each primary category. A mixed methods research was performed and total 4905 popular apps were observed. The original categorization was proved to be substantial reliable but need further improvement. The representative functionality stems for each category were identified. This paper may provide some fusion research experience and methodological suggestions in categorization research field and improve app store's categorization in discoverability.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.39-46
• /
• 2022

In this paper, we propose a multi-task model that can simultaneously predict general-purpose tasks such as part-of-speech tagging, lemmatization, and dependency parsing using the UD Korean Kaist v2.3 corpus. The proposed model thus applies the self-attention technique of the BERT model and the graph-based Biaffine attention technique by fine-tuning the multilingual BERT and the two Korean-specific BERTs such as KR-BERT and KoBERT. The performances of the proposed model are compared and analyzed using the multilingual version of BERT and the two Korean-specific BERT language models.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.163-170
• /
• 2017

Despite the rise of studies in spoken to sign language translation, low-resource problems of sign language corpus have been rarely addressed. As a first step towards translating from spoken to sign language, we addressed the problems arising from resource scarcity when translating spoken language to manual signals translation using statistical machine translation techniques. More specifically, we proposed three preprocessing methods: 1) paraphrase generation, which increases the size of the corpora, 2) lemmatization, which increases the frequency of each word in the corpora and the translatability of new input words in spoken language, and 3) elimination of function words that are not glossed into manual signals, which match the corresponding constituents of the bilingual sentence pairs. In our experiments, we used different types of English-American sign language parallel corpora. The experimental results showed that the system with each method and the combination of the methods improved the quality of manual signals translation, regardless of the type of the corpora.

• Journal of Information Science Theory and Practice
• /
• v.7 no.1
• /
• pp.29-38
• /
• 2019

Information retrieval is the challenge of the Web 2.0 world. The experiment of knowledge organisation in the context of abundant information available from various sources proves a major hurdle in obtaining information retrieval with greater precision and recall. The fast-changing landscape of information organisation through social networking sites at a personal level creates a world of opportunities for data scientists and also library professionals to assimilate the social data with expert created data. Thus, folksonomies or social tags play a vital role in information organisation and retrieval. The comparison of these user-created tags with expert-created index terms, author keywords and title words, will throw light on the differentiation between these sets of data. Such comparative studies show revelation of a new set of terms to enhance subject access and reflect the extent of similarity between user-generated tags and other set of terms. The CiteULike tags extracted from 5,150 scholarly journal articles in marine science were compared with corresponding Aquatic Science and Fisheries Abstracts descriptors, author keywords, and title terms. The Jaccard similarity coefficient method was employed to compare the social tags with the above mentioned wordsets, and results proved the presence of user-generated keywords in Aquatic Science and Fisheries Abstracts descriptors, author keywords, and title words. While using information retrieval techniques like stemmer and lemmatization, the results were found to enhance keywords to subject access.