• ETRI Journal
• /
• v.46 no.1
• /
• pp.35-47
• /
• 2024

This study introduces CR-M-SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding-based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost-effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR-M-SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high-recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.

• The Journal of Information Systems
• /
• v.21 no.3
• /
• pp.137-161
• /
• 2012

The increasing interest in big data analysis using various data mining techniques indicates that many commercial data mining tools now need to be equipped with fundamental text analysis modules. The most essential prerequisite for accurate analysis of text documents is an understanding of the exact semantics of each term in a document. The main difficulties in understanding the exact semantics of terms are mainly attributable to homonym and synonym problems, which is a traditional problem in the natural language processing field. Some major text mining tools provide a thesaurus to solve these problems, but a thesaurus cannot be used to resolve complex synonym problems. Furthermore, the use of a thesaurus is irrelevant to the issue of homonym problems and hence cannot solve them. In this paper, we propose a semantic text mining methodology that uses ontologies to improve the quality of text mining results by resolving the semantic ambiguity caused by homonym and synonym problems. We evaluate the practical applicability of the proposed methodology by performing a classification analysis to predict customer churn using real transactional data and Q&A articles from the "S" online shopping mall in Korea. The experiments revealed that the prediction model produced by our proposed semantic text mining method outperformed the model produced by traditional text mining in terms of prediction accuracy such as the response, captured response, and lift.

• Journal of Information Science Theory and Practice
• /
• v.9 no.4
• /
• pp.15-34
• /
• 2021

Text clustering is one of the most commonly used methods for detecting themes or types of documents. Text clustering is used in many fields, but its effectiveness is still not sufficient to be used for the understanding of Arabic text, especially with respect to terms extraction, unsupervised feature selection, and clustering algorithms. In most cases, terms extraction focuses on nouns. Clustering simplifies the understanding of an Arabic text like the text of the Quran; it is important not only for Muslims but for all people who want to know more about Islam. This paper discusses the complexity and limitations of Arabic text clustering in the Quran based on their themes. Unsupervised feature selection does not consider the relationships between the selected features. One weakness of clustering algorithms is that the selection of the optimal initial centroid still depends on chances and manual settings. Consequently, this paper reviews literature about the three major stages of Arabic clustering: terms extraction, unsupervised feature selection, and clustering. Six experiments were conducted to demonstrate previously un-discussed problems related to the metrics used for feature selection and clustering. Suggestions to improve clustering of the Quran based on themes are presented and discussed.

• International Journal of Knowledge Content Development & Technology
• /
• v.13 no.2
• /
• pp.23-35
• /
• 2023

Word templates exist for select journals, and their primary objective is to facilitate submissions to those journals, thereby optimizing editors' and publishers' time and resources by ensuring that the desired style (e.g., of sections, references, etc.) is followed. However, if multiple unrelated authors use the exact same template, a risk exists that some text might be erroneously cloned if template-based papers are not carefully screened by authors, journal editors or proof copyeditors. Elsevier Procedia® was used as an example. Select cloned text, presumably derived from MS Word templates used for submissions to Elsevier Procedia® journals, was assessed using Science Direct. Typically, in academic publishing, identical text is screened using text similarity software during the submission process, and if detected, may be flagged as plagiarism. After searching for "heading should be left justified, bold, with the first letter capitalized", 44 Elsevier Procedia® papers were found to be positive for vestigial template text. The integrity of the information in these papers has been compromised, so these errors should be corrected with an erratum, or in the case of extensive errors and vast tracts (e.g., pages long) of template text, papers should be retracted and republished.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1111-1123
• /
• 2023

In recent years, as generative models have developed, research that threatens them has also been actively conducted. We propose a new membership inference attack against text-to-image model. Existing membership inference attacks on Text-to-Image models produced a single image as captions of query images. On the other hand, this paper uses personalized embedding in query images through Textual Inversion. And we propose a membership inference attack that effectively generates multiple images as a method of generating Adversarial Prompt. In addition, the membership inference attack is tested for the first time on the Stable Diffusion model, which is attracting attention among the Text-to-Image models, and achieve an accuracy of up to 1.00.

• Journal of information and communication convergence engineering
• /
• v.15 no.3
• /
• pp.170-174
• /
• 2017

Nowadays, people share and discuss scientific papers on social media such as the Web 2.0, big data, online forums, blogs, Twitter, Facebook and scholar community, etc. In addition to a variety of metrics such as numbers of citation, download, recommendation, etc., paper review text is also one of the effective resources for the study of scientific impact. The social media tools improve the research process: recording a series online scholarly behaviors. This paper aims to research the huge amount of paper reviews which have generated in the social media platforms to explore the implicit information about research papers. We implemented and shown the result of text mining on review texts using R language. And we found that Zika virus was the research hotspot and association research methods were widely used in 2016. We also mined the news review about one paper and derived the public opinion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.7
• /
• pp.3578-3593
• /
• 2017

Given two collections of objects that carry both spatial and textual information in the form of tags, a $\text\underline{S}patio$-$\text\underline{T}extual$-based object $\text\underline{S}imilarity$ $\text\underline{JOIN}$ (ST-SJOIN) retrieves the pairs of objects that are textually similar and spatially close. In this paper, we have proposed a block index-based approach called BIST-JOIN to facilitate the efficient ST-SJOIN processing. In this approach, a dual-feature distance plane (DFDP) is first partitioned into some blocks based on four segmentation schemes, and the ST-SJOIN is then transformed into searching the object pairs falling in some affected blocks in the DFDP. Extensive experiments on real and synthetic datasets demonstrate that our proposed join method outperforms the state-of-the-art solutions.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.646-654
• /
• 2007

In recent years, the use of text inserted into TV contents has grown to provide viewers with better visual understanding. In this paper, video text is defined as superimposed text region located of the bottom of video. Video text extraction is the first step for video information retrieval and video indexing. Most of video text detection and extraction methods in the previous work are based on text color, contrast between text and background, edge, character filter, and so on. However, the video text extraction has big problems due to low resolution of video and complex background. To solve these problems, we propose a method to extract text from videos using the Harris corner detector. The proposed algorithm consists of four steps: corer map generation using the Harris corner detector, extraction of text candidates considering density of comers, text region determination using labeling, and post-processing. The proposed algorithm is language independent and can be applied to texts with various colors. Text region update between frames is also exploited to reduce the processing time. Experiments are performed on diverse videos to confirm the efficiency of the proposed method.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.117-120
• /
• 2002

In this paper, we propose a new text watermarking method using space coding and PN sequence. A PN sequence generated from user message modifies the space between words in each line. The detection can be done without original text image using the average space with in the text. Experimental results show that proposed method has the invisible property and robustness to the attack such as the elimination of words in the text.

• Journal of information and communication convergence engineering
• /
• v.4 no.4
• /
• pp.174-179
• /
• 2006

In this paper we present a text detection method inspired by wavelet packet analysis and improved fuzzy clustering algorithm(IAFC).This approach assumes that the text and non-text regions are considered as two different texture regions. The text detection is achieved by using wavelet packet analysis as a feature analysis. The wavelet packet analysis is a method of wavelet decomposition that offers a richer range of possibilities for document image. From these multi scale features, we adapt the improved fuzzy clustering algorithm based on the unsupervised learning rule. The results show that our text detection method is effective for document images scanned from newspapers and journals.