• 제목/요약/키워드: text features

검색결과 570건 처리시간 0.029초

CRF를 이용한 운율경계추성 성능개선 (Improvements on Phrase Breaks Prediction Using CRF (Conditional Random Fields))

  • 김승원;이근배;김병창
    • 대한음성학회지:말소리
    • /
    • 제57호
    • /
    • pp.139-152
    • /
    • 2006
  • In this paper, we present a phrase break prediction method using CRF(Conditional Random Fields), which has good performance at classification problems. The phrase break prediction problem was mapped into a classification problem in our research. We trained the CRF using the various linguistic features which was extracted from POS(Part Of Speech) tag, lexicon, length of word, and location of word in the sentences. Combined linguistic features were used in the experiments, and we could collect some linguistic features which generate good performance in the phrase break prediction. From the results of experiments, we can see that the proposed method shows improved performance on previous methods. Additionally, because the linguistic features are independent of each other in our research, the proposed method has higher flexibility than other methods.

  • PDF

In-depth Recommendation Model Based on Self-Attention Factorization

  • Hongshuang Ma;Qicheng Liu
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제17권3호
    • /
    • pp.721-739
    • /
    • 2023
  • Rating prediction is an important issue in recommender systems, and its accuracy affects the experience of the user and the revenue of the company. Traditional recommender systems use Factorization Machinesfor rating predictions and each feature is selected with the same weight. Thus, there are problems with inaccurate ratings and limited data representation. This study proposes a deep recommendation model based on self-attention Factorization (SAFMR) to solve these problems. This model uses Convolutional Neural Networks to extract features from user and item reviews. The obtained features are fed into self-attention mechanism Factorization Machines, where the self-attention network automatically learns the dependencies of the features and distinguishes the weights of the different features, thereby reducing the prediction error. The model was experimentally evaluated using six classes of dataset. We compared MSE, NDCG and time for several real datasets. The experiment demonstrated that the SAFMR model achieved excellent rating prediction results and recommendation correlations, thereby verifying the effectiveness of the model.

작성자 분석 기반의 공격 메일 탐지를 위한 분류 모델 (A Classification Model for Attack Mail Detection based on the Authorship Analysis)

  • 홍성삼;신건윤;한명묵
    • 인터넷정보학회논문지
    • /
    • 제18권6호
    • /
    • pp.35-46
    • /
    • 2017
  • 최근 사이버보안에서 악성코드를 이용한 공격은 메일에 악성코드를 첨부하여 이를 사용자가 실행하도록 유도하여 공격을 수행하는 형태가 늘어나고 있다. 특히 문서형태의 파일을 첨부하여 사용자가 쉽게 실행하게 되어 위험하다. 저자 분석은 NLP(Neutral Language Process) 및 텍스트 마이닝 분야에서 연구되어지고 있는 분야이며, 특정 언어로 이루어진 텍스트 문장, 글, 문서를 분석하여 작성한 저자를 분석하는 방법들은 연구하는 분야이다. 공격 메일의 경우 일정 공격자에 의해 작성되어지기 때문에 메일 내용 및 첨부된 문서 파일을 분석하여 해당 저자를 식별하면 정상메일과 더욱 구별된 특징들을 발견할 수 있으며, 탐지 정확도를 향상시킬 수 있다. 본 논문에서는 기존의 기계학습 기반의 스팸메일 탐지 모델에서 사용되는 특징들과 문서의 저자 분석에 사용되는 특징들로부터 공격메일을 분류 및 탐지를 할 수 있는 feature vector 및 이에 적합한 IADA2(Intelligent Attack mail Detection based on Authorship Analysis)탐지 모델을 제안하였다. 단순히 단어 기반의 특징들로 탐지하던 스팸메일 탐지 모델들을 개선하고, n-gram을 적용하여 단어의 시퀀스 특성을 반영한 특징을 추출하였다. 실험결과, 특징의 조합과 특징선택 기법, 적합한 모델들에 따라 성능이 개선됨을 검증할 수 있었으며, 제안하는 모델의 성능의 우수성과 개선 가능성을 확인할 수 있었다.

Design and Development of a Multimodal Biomedical Information Retrieval System

  • Demner-Fushman, Dina;Antani, Sameer;Simpson, Matthew;Thoma, George R.
    • Journal of Computing Science and Engineering
    • /
    • 제6권2호
    • /
    • pp.168-177
    • /
    • 2012
  • The search for relevant and actionable information is a key to achieving clinical and research goals in biomedicine. Biomedical information exists in different forms: as text and illustrations in journal articles and other documents, in images stored in databases, and as patients' cases in electronic health records. This paper presents ways to move beyond conventional text-based searching of these resources, by combining text and visual features in search queries and document representation. A combination of techniques and tools from the fields of natural language processing, information retrieval, and content-based image retrieval allows the development of building blocks for advanced information services. Such services enable searching by textual as well as visual queries, and retrieving documents enriched by relevant images, charts, and other illustrations from the journal literature, patient records and image databases.

Learner-Generated Digital Listening Materials Using Text-to-Speech for Self-Directed Listening Practice

  • Moon, Dosik
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제12권4호
    • /
    • pp.148-155
    • /
    • 2020
  • This study investigated learners' perceptions of using self-generated listening materials based on Text to Speech. After taking an online training session to learn how to make listening materials for extensive listening practice outside the classroom, the learners were engaged in practice with self-generated listening materials for 10 weeks in a self-directed way. The results show that a majority of the learners found the TTS-based listening materials helpful to reduce anxiety toward listening and enhance self-confidence and motivation, with a positive effect on improving their listening ability. The learners' general satisfaction can be attributed to some beneficial features of TTS-based listening material, including freedom to choose what they want to learn, convenient accessibility to the material, availability of various native speakers' voices, and novelty of digital tools. This suggests that TTS-based digital listening materials can be a useful educational tool to support learners' self-directed listening practice outside the classroom in EFL settings.

단어 분류에 기반한 텍스트 영상 워터마킹 알고리즘 (An Algorithm for Text Image Watermarking based on Word Classification)

  • 김영원;오일석
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제32권8호
    • /
    • pp.742-751
    • /
    • 2005
  • 본 논문은 단어 분류에 기반한 새로운 텍스트 영상 워터마킹 알고리즘을 제안한다. 간단한 특징을 이용하여 단어를 K개로 분류한다. 이웃한 몇 개의 단어들을 조합하여 세그먼트를 구성하고, 세그먼트에 속한 단어들의 부류에 의해 세그먼트 또한 분류된다. 각 세그먼트에 동일한 양의 신호가 삽입된다. 신호 삽입은 세그먼트 부류가 갖는 단어 간 공백의 통계값을 조작함으로써 이루어진다. 몇 가지 기준에 따라 기존 단어 이동 알고리즘과의 주관적인 비교가 제시된다.

Modality-Based Sentence-Final Intonation Prediction for Korean Conversational-Style Text-to-Speech Systems

  • Oh, Seung-Shin;Kim, Sang-Hun
    • ETRI Journal
    • /
    • 제28권6호
    • /
    • pp.807-810
    • /
    • 2006
  • This letter presents a prediction model for sentence-final intonations for Korean conversational-style text-to-speech systems in which we introduce the linguistic feature of 'modality' as a new parameter. Based on their function and meaning, we classify tonal forms in speech data into tone types meaningful for speech synthesis and use the result of this classification to build our prediction model using a tree structured classification algorithm. In order to show that modality is more effective for the prediction model than features such as sentence type or speech act, an experiment is performed on a test set of 970 utterances with a training set of 3,883 utterances. The results show that modality makes a higher contribution to the determination of sentence-final intonation than sentence type or speech act, and that prediction accuracy improves up to 25% when the feature of modality is introduced.

  • PDF

SNS 특징정보를 활용한 마르코프 논리 네트워크 기반의 단문 텍스트 분류 방법 (A Method for Short Text Classification using SNS Feature Information based on Markov Logic Networks)

  • 이은지;김판구
    • 한국멀티미디어학회논문지
    • /
    • 제20권7호
    • /
    • pp.1065-1072
    • /
    • 2017
  • As smart devices and social network services (SNSs) become increasingly pervasive, individuals produce large amounts of data in real time. Accordingly, studies on unstructured data analysis are actively being conducted to solve the resultant problem of information overload and to facilitate effective data processing. Many such studies are conducted for filtering inappropriate information. In this paper, a feature-weighting method considering SNS-message features is proposed for the classification of short text messages generated on SNSs, using Markov logic networks for category inference. The performance of the proposed method is verified through a comparison with an existing frequency-based classification methods.

전문(全文) DB 구축(構築)에 의한 한국통신연구정보관리(韓國通信硏究情報管理) 시스템 개발(開發) (Development of KTRIMS Using the Technology of Full Text DB Construction)

  • 이상엽;안현수;이양옥
    • 정보관리연구
    • /
    • 제24권1호
    • /
    • pp.1-20
    • /
    • 1993
  • 한국통신(韓國通信) 연구개발단(硏究開發團)에서는 사내(社內) 각 연구부서(硏究部署)에서 발생하는 각종 최신 연구정보(硏究情報)의 원문(原文)을 축적(蓄積) 공동활용(共同活用)하기 위하여 한국통신연구정보관리(韓國通信硏究情報管理) 시스템(KTRIMS)을 개발(開發)하였으며, 본(本) 고(稿)에서는 KTRIMS의 구성(構成)과 특징(特徵)을 중심(中心)으로 기술(記述)하였다.

  • PDF

Design and Implementation of Web Crawler with Real-Time Keyword Extraction based on the RAKE Algorithm

  • Zhang, Fei;Jang, Sunggyun;Joe, Inwhee
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2017년도 추계학술발표대회
    • /
    • pp.395-398
    • /
    • 2017
  • We propose a web crawler system with keyword extraction function in this paper. Researches on the keyword extraction in existing text mining are mostly based on databases which have already been grabbed by documents or corpora, but the purpose of this paper is to establish a real-time keyword extraction system which can extract the keywords of the corresponding text and store them into the database together while grasping the text of the web page. In this paper, we design and implement a crawler combining RAKE keyword extraction algorithm. It can extract keywords from the corresponding content while grasping the content of web page. As a result, the performance of the RAKE algorithm is improved by increasing the weight of the important features (such as the noun appearing in the title). The experimental results show that this method is superior to the existing method and it can extract keywords satisfactorily.