• 한국인터넷방송통신학회논문지
• /
• 제13권5호
• /
• pp.37-47
• /
• 2013

텍스트 마이닝은 비정형화된 텍스트를 분석하여 그 안에 내재된 패턴, 추세, 분포 등의 고급정보들을 추출하는 분야이다. 텍스트 마이닝은 기본적으로 비정형 데이터를 가정하므로 텍스트를 단순화된 모델로 표현하는 것이 필요하다. 현재까지 가장 많이 사용되고 있는 모델은 텍스트를 단순한 단어들의 집합으로 표현한 벡터공간 모델이다. 그러나 최근 들어 단어들의 의미적 관계까지 표현하기 위해 그래프를 이용한 텍스트 표현 모델을 많이 사용하고 있다. 본 논문에서는 텍스트 마이닝을 위한 기존의 연구 중에서 그래프에 기반한 텍스트 표현 모델의 방법들과 그들의 특징들을 기술한다. 또한 그래프 기반 텍스트 마이닝의 향후 발전방향에 대해서도 논한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2390-2406
• /
• 2022

Scene text recognition has important application value and attracted the interest of plenty of researchers. At present, many methods have achieved good results, but most of the existing approaches attempt to improve the performance of scene text recognition from the image level. They have a good effect on reading regular scene texts. However, there are still many obstacles to recognizing text on low-quality images such as curved, occlusion, and blur. This exacerbates the difficulty of feature extraction because the image quality is uneven. In addition, the results of model testing are highly dependent on training data, so there is still room for improvement in scene text recognition methods. In this work, we present a natural scene text recognizer to improve the recognition performance from the feature level, which contains feature representation and feature enhancement. In terms of feature representation, we propose an efficient feature extractor combined with Representative Batch Normalization and ResNet. It reduces the dependence of the model on training data and improves the feature representation ability of different instances. In terms of feature enhancement, we use a feature enhancement network to expand the receptive field of feature maps, so that feature maps contain rich feature information. Enhanced feature representation capability helps to improve the recognition performance of the model. We conducted experiments on 7 benchmarks, which shows that this method is highly competitive in recognizing both regular and irregular texts. The method achieved top1 recognition accuracy on four benchmarks of IC03, IC13, IC15, and SVTP.

• 한국전자거래학회지
• /
• 제19권3호
• /
• pp.107-123
• /
• 2014

텍스트마이닝 연구의 기본적인 난제는 기존 텍스트 표현모델이 자연어 문장으로 기술된 텍스트 데이터로부터 의미 또는 개념 정보를 표현하지 않는데 기인한다. 기존 텍스트 표현모델인 벡터공간 모델(vector space model), 불리언 모델(Boolean model), 통계 모델(statistical model), 텐서공간 모델(tensor space model) 등은 'Bag-of-Words' 방식에 바탕을 두고 있다. 이러한 텍스트 모델들은 텍스트에 포함된 단어와 그것의 출현 횟수만으로 텍스트를 표현하므로, 단어의 함축 의미, 단어의 순서 및 텍스트의 구조를 전혀 표현하지 못한다. 대부분의 텍스트 마이닝 기술은 대상 문서를 'Bag-of-Words' 방식의 텍스트 모델로 표현함을 전제로 하여 발전하여 왔다. 하지만 오늘날 빅데이터 시대를 맞이하여 방대한 규모의 텍스트 데이터를 보다 정밀하게 분석할 수 있는 새로운 패러다임의 표현모델을 요구하고 있다. 본 논문에서 제안하는 텍스트 표현모델은 개념공간을 문서 및 단어와 동등한 매핑 공간으로 상정하여, 그 세 가지 공간에 대한 연관 관계를 모두 표현한다. 개념공간의 구성을 위해서 위키피디어 데이터를 활용하며, 하나의 개념은 하나의 위키피디어 페이지로부터 정의된다. 결과적으로 주어진 텍스트 문서집합을 의미적으로 해석이 가능한 3차 텐서(3-order tensor)로 표현하게 되며, 따라서 제안 모델을 텍스트 큐보이드 모델이라 명명한다. 20Newsgroup 문서집합을 사용하여 문서 및 개념 수준의 클러스터링 정확도를 평가함으로써, 제안 모델이 'Bag-of-Word' 방식의 대표적 모델인 벡터공간 모델에 비해 우수함을 보인다.

• 대한음성학회지:말소리
• /
• 제53호
• /
• pp.75-92
• /
• 2005

Prosody Generation Based on C-ToBI Representation for Text-to-SpeechSeungwon Kim, Yu Zheng, Gary Geunbae Lee, Byeongchang KimProsody modeling is critical in developing text-to-speech (TTS) systems where speech synthesis is used to automatically generate natural speech. In this paper, we present a prosody generation architecture based on Chinese Tone and Break Index (C-ToBI) representation. ToBI is a multi-tier representation system based on linguistic knowledge to transcribe events in an utterance. The TTS system which adopts ToBI as an intermediate representation is known to exhibit higher flexibility, modularity and domain/task portability compared with the direct prosody generation TTS systems. However, the cost of corpus preparation is very expensive for practical-level performance because the ToBI labeled corpus has been manually constructed by many prosody experts and normally requires a large amount of data for accurate statistical prosody modeling. This paper proposes a new method which transcribes the C-ToBI labels automatically in Chinese speech. We model Chinese prosody generation as a classification problem and apply conditional Maximum Entropy (ME) classification to this problem. We empirically verify the usefulness of various natural language and phonology features to make well-integrated features for ME framework.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2178-2198
• /
• 2024

Graph-based document models have good capabilities to reveal inter-dependencies among unstructured text data. Natural language processing (NLP) systems that use such models as an intermediate representation have shown good performance. This paper proposes a novel fuzzy graph-based document model and to demonstrate its effectiveness by applying fuzzy logic tools for text summarization. The proposed system accepts a text document as input and identifies some of its sentence level features, namely sentence position, sentence length, numerical data, thematic word, proper noun, title feature, upper case feature, and sentence similarity. The fuzzy membership value of each feature is computed from the sentences. We also propose a novel algorithm to construct the fuzzy graph as an intermediate representation of the input document. The Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metric is used to evaluate the model. The evaluation based on different quality metrics was also performed to verify the effectiveness of the model. The ANOVA test confirms the hypothesis that the proposed model improves the summarizer performance by 10% when compared with the state-of-the-art summarizers employing alternate intermediate representations for the input text.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권9호
• /
• pp.596-603
• /
• 2015

개념망(Concept Network)은 시멘틱 검색, 개인화 검색, 추천, 텍스트마이닝 기법의 개선 등에 필수적인 지식베이스이다. 최근 효과적인 개념망 구축을 위해 온톨로지를 기반으로 하여 개념의 표현을 확장시키는 연구가 활발하다. 이에 본 논문은 World Knowledge로 평가받고 있는 위키피디아 데이터를 '개념' 집합의 원천으로 활용하여 3차원 텍스트 표현 모델 기반 개념망을 구축하는 기법을 제안한다. 사실상 개념들 간의 관계 정보는 시간의 흐름에 따라 변동하기 때문에, 텍스트 문서로부터 도출되는 '개념'은 Formal Concept Analysis 이론체계의 개념에 따르는 것이 바람직하다. 이를 위해 본 논문은 하나의 개념을 '단어'와 '문서' 간의 2차원 행렬로 표현하여 문서집합에 잠재된 개념간의 연관망을 보다 정확하게 생성하게 한다.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.863-875
• /
• 2017

The traditional text similarity measurement methods based on word frequency vector ignore the semantic relationships between words, which has become the obstacle to text similarity calculation, together with the high-dimensionality and sparsity of document vector. To address the problems, the improved singular value decomposition is used to reduce dimensionality and remove noises of the text representation model. The optimal number of singular values is analyzed and the semantic relevance between words can be calculated in constructed semantic space. An inverted index construction algorithm and the similarity definitions between vectors are proposed to calculate the similarity between two documents on the semantic level. The experimental results on benchmark corpus demonstrate that the proposed method promotes the evaluation metrics of F-measure.

• ETRI Journal
• /
• 제44권5호
• /
• pp.794-804
• /
• 2022

Transformer models have had a great impact on natural language processing (NLP) in recent years by realizing outstanding and efficient contextualized language models. Recent studies have used transformer-based language models for various NLP tasks, including Persian named entity recognition (NER). However, in complex tasks, for example, NER, it is difficult to determine which contextualized embedding will produce the best representation for the tasks. Considering the lack of comparative studies to investigate the use of different contextualized pretrained models with sequence modeling classifiers, we conducted a comparative study about using different classifiers and embedding models. In this paper, we use different transformer-based language models tuned with different classifiers, and we evaluate these models on the Persian NER task. We perform a comparative analysis to assess the impact of text representation and text classification methods on Persian NER performance. We train and evaluate the models on three different Persian NER datasets, that is, MoNa, Peyma, and Arman. Experimental results demonstrate that XLM-R with a linear layer and conditional random field (CRF) layer exhibited the best performance. This model achieved phrase-based F-measures of 70.04, 86.37, and 79.25 and word-based F scores of 78, 84.02, and 89.73 on the MoNa, Peyma, and Arman datasets, respectively. These results represent state-of-the-art performance on the Persian NER task.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2407-2424
• /
• 2022

Recently, Transformer has made great progress in video retrieval tasks due to its high representation capability. For the structure of a Transformer, the cascaded self-attention modules are capable of capturing long-distance feature dependencies. However, the local feature details are likely to have deteriorated. In addition, increasing the depth of the structure is likely to produce learning bias in the learned features. In this paper, an improved Transformer structure named TransDCS (Transformer with Dynamic Convolution and Shortcut) is proposed. A Multi-head Conv-Self-Attention module is introduced to model the local dependencies and improve the efficiency of local features extraction. Meanwhile, the augmented shortcuts module based on a dual identity matrix is applied to enhance the conduction of input features, and mitigate the learning bias. The proposed model is tested on MSRVTT, LSMDC and Activity-Net benchmarks, and it surpasses all previous solutions for the video-text retrieval task. For example, on the LSMDC benchmark, a gain of about 2.3% MdR and 6.1% MnR is obtained over recently proposed multimodal-based methods.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.405-414
• /
• 2007

This paper describes a preliminary work on prosody modeling aspect of a text-to-speech system for Thai. Specifically, the model is designed to predict symbolic markers from text (i.e., prosodic phrase boundaries, accent, and intonation boundaries), and then using these markers to generate pitch, intensity, and durational patterns for the synthesis module of the system. In this paper, a novel method for annotating the prosodic structure of Thai sentences based on dependency representation of syntax is presented. The goal of the annotation process is to predict from text the rhythm of the input sentence when spoken according to its intended meaning. The encoding of the prosodic structure is established by minimizing speech disrhythmy while maintaining the congruency with syntax. That is, each word in the sentence is assigned a prosodic feature called strength dynamic which is based on the dependency representation of syntax. The strength dynamics assigned are then used to obtain rhythmic groupings in terms of a phonological unit called foot. Finally, the foot structure is used to predict the durational pattern of the input sentence. The aforementioned process has been tested on a set of ambiguous sentences, which represents various structural ambiguities involving five types of compounds in Thai.