• Title/Summary/Keyword: Conditional Random Fields

Search Result 58, Processing Time 0.046 seconds

CRFs versus Bi-LSTM/CRFs: Automatic Word Spacing Perspective (CRFs와 Bi-LSTM/CRFs의 비교 분석: 자동 띄어쓰기 관점에서)

  • Yoon, Ho;Kim, Chang-Hyun;Cheon, Min-Ah;Park, Ho-min;Namgoong, Young;Choi, Minseok;Kim, Jae-Hoon
    • Annual Conference on Human and Language Technology
    • /
    • 2018.10a
    • /
    • pp.189-192
    • /
    • 2018
  • 자동 띄어쓰기란 컴퓨터를 사용하여 띄어쓰기가 수행되어 있지 않은 문장에 대해 띄어쓰기를 수행하는 것이다. 이는 자연언어처리 분야에서 형태소 분석 전에 수행되는 과정으로, 띄어쓰기에 오류가 발생할 경우, 형태소 분석이나 구문 분석 등에 영향을 주어 그 결과의 모호성을 높이기 때문에 매우 중요한 전처리 과정 중 하나이다. 본 논문에서는 기계학습의 방법 중 하나인 CRFs(Conditional Random Fields)를 이용하여 자동 띄어쓰기를 수행하고 심층 학습의 방법 중 하나인 양방향 LSTM/CRFs (Bidirectional Long Short Term Memory/CRFs)를 이용하여 자동 띄어쓰기를 수행한 뒤 각 모델의 성능을 비교하고 분석한다. CRFs 모델이 양방향 LSTM/CRFs모델보다 성능이 약간 더 높은 모습을 보였다. 따라서 소형 기기와 같은 환경에서는 CRF와 같은 모델을 적용하여 모델의 경량화 및 시간복잡도를 개선하는 것이 훨씬 더 효과적인 것으로 생각된다.

  • PDF

Performance Comparison of Recurrent Neural Networks and Conditional Random Fields in Biomedical Named Entity Recognition (의생명 분야의 개체명 인식에서 순환형 신경망과 조건적 임의 필드의 성능 비교)

  • Jo, Byeong-Cheol;Kim, Yu-Seop
    • Annual Conference on Human and Language Technology
    • /
    • 2016.10a
    • /
    • pp.321-323
    • /
    • 2016
  • 최근 연구에서 기계학습 중 지도학습 방법으로 개체명 인식을 하고 있다. 그러나 지도 학습 방법은 데이터를 만드는 비용과 시간이 많이 필요로 한다. 본 연구에서는 주석 된 말뭉치를 사용하여 지도 학습 방법을 사용 한다. 의생명 개체명 인식은 Protein, RNA, DNA, Cell type, Cell line 등을 포함한 텍스트 처리에 중요한 기초 작업입니다. 그리고 의생명 지식 검색에서 가장 기본과 핵심 작업 중 하나이다. 본 연구에서는 순환형 신경망과 워드 임베딩을 자질로 사용한 조건적 임의 필드에 대한 성능을 비교한다. 조건적 임의 필드에 N_Gram만을 자질로 사용한 것을 기준점으로 설정 하였고, 기준점의 결과는 70.09% F1 Score이다. RNN의 jordan type은 60.75% F1 Score, elman type은 58.80% F1 Score의 성능을 보여준다. 조건적 임의 필드에 CCA, GLOVE, WORD2VEC을 사용 한 결과는 각각 72.73% F1 Score, 72.74% F1 Score, 72.82% F1 Score의 성능을 얻을 수 있다.

  • PDF

Development of Tourism Information Named Entity Recognition Datasets for the Fine-tune KoBERT-CRF Model

  • Jwa, Myeong-Cheol;Jwa, Jeong-Woo
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.14 no.2
    • /
    • pp.55-62
    • /
    • 2022
  • A smart tourism chatbot is needed as a user interface to efficiently provide smart tourism services such as recommended travel products, tourist information, my travel itinerary, and tour guide service to tourists. We have been developed a smart tourism app and a smart tourism information system that provide smart tourism services to tourists. We also developed a smart tourism chatbot service consisting of khaiii morpheme analyzer, rule-based intention classification, and tourism information knowledge base using Neo4j graph database. In this paper, we develop the Korean and English smart tourism Name Entity (NE) datasets required for the development of the NER model using the pre-trained language models (PLMs) for the smart tourism chatbot system. We create the tourism information NER datasets by collecting source data through smart tourism app, visitJeju web of Jeju Tourism Organization (JTO), and web search, and preprocessing it using Korean and English tourism information Name Entity dictionaries. We perform training on the KoBERT-CRF NER model using the developed Korean and English tourism information NER datasets. The weight-averaged precision, recall, and f1 scores are 0.94, 0.92 and 0.94 on Korean and English tourism information NER datasets.

CRFNet: Context ReFinement Network used for semantic segmentation

  • Taeghyun An;Jungyu Kang;Dooseop Choi;Kyoung-Wook Min
    • ETRI Journal
    • /
    • v.45 no.5
    • /
    • pp.822-835
    • /
    • 2023
  • Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

Utilizing Experiences of Supervisor in Sequential Learning for Multilayer Perceptron (지도 경험을 활용한 다계층 퍼셉트론의 순차적 학습 방법)

  • Lee, Jae-Young;Kim, Hwang-Soo
    • Journal of KIISE:Software and Applications
    • /
    • v.37 no.10
    • /
    • pp.723-735
    • /
    • 2010
  • Evaluating the level of achievement and providing the knowledge which is appropriate at the evaluated level have great influence in studying of the human beings. This shows the importance of the order of training and the training order should be considered in machine learning. In this research, to assess the influence of the order of training, we propose a method of controlling the order of training samples utilizing the experience of supervisor in the training of MLP. The supervisor finds out the current state of MLP using teaching experience and student evaluation, and then selects the most instructive sample for MLP in that state. We use CRF to represent and utilize the experience of supervisor. While the proposed method is similar to active learning in selecting samples, it is basically different in that selection is not to reduce the number of samples to be used but to assist the learning progress. The result from classification problem shows that the method is usually effective in terms of time taken in training in contrast to random selection.

Korean Semantic Role Labeling Using Case Frame Dictionary and Subcategorization (격틀 사전과 하위 범주 정보를 이용한 한국어 의미역 결정)

  • Kim, Wan-Su;Ock, Cheol-Young
    • Journal of KIISE
    • /
    • v.43 no.12
    • /
    • pp.1376-1384
    • /
    • 2016
  • Computers require analytic and processing capability for all possibilities of human expression in order to process sentences like human beings. Linguistic information processing thus forms the initial basis. When analyzing a sentence syntactically, it is necessary to divide the sentence into components, find obligatory arguments focusing on predicates, identify the sentence core, and understand semantic relations between the arguments and predicates. In this study, the method applied a case frame dictionary based on The Korean Standard Dictionary of The National Institute of the Korean Language; in addition, we used a CRF Model that constructed subcategorization of predicates as featured in Korean Lexical Semantic Network (UWordMap) for semantic role labeling. Automatically tagged semantic roles based on the CRF model, which established the information of words, predicates, the case-frame dictionary and hypernyms of words as features, were used. This method demonstrated higher performance in comparison with the existing method, with accuracy rate of 83.13% as compared to 81.2%, respectively.

KONG-DB: Korean Novel Geo-name DB & Search and Visualization System Using Dictionary from the Web (KONG-DB: 웹 상의 어휘 사전을 활용한 한국 소설 지명 DB, 검색 및 시각화 시스템)

  • Park, Sung Hee
    • Journal of the Korean Society for information Management
    • /
    • v.33 no.3
    • /
    • pp.321-343
    • /
    • 2016
  • This study aimed to design a semi-automatic web-based pilot system 1) to build a Korean novel geo-name, 2) to update the database using automatic geo-name extraction for a scalable database, and 3) to retrieve/visualize the usage of an old geo-name on the map. In particular, the problem of extracting novel geo-names, which are currently obsolete, is difficult to solve because obtaining a corpus used for training dataset is burden. To build a corpus for training data, an admin tool, HTML crawler and parser in Python, crawled geo-names and usages from a vocabulary dictionary for Korean New Novel enough to train a named entity tagger for extracting even novel geo-names not shown up in a training corpus. By means of a training corpus and an automatic extraction tool, the geo-name database was made scalable. In addition, the system can visualize the geo-name on the map. The work of study also designed, implemented the prototype and empirically verified the validity of the pilot system. Lastly, items to be improved have also been addressed.

A Korean Community-based Question Answering System Using Multiple Machine Learning Methods (다중 기계학습 방법을 이용한 한국어 커뮤니티 기반 질의-응답 시스템)

  • Kwon, Sunjae;Kim, Juae;Kang, Sangwoo;Seo, Jungyun
    • Journal of KIISE
    • /
    • v.43 no.10
    • /
    • pp.1085-1093
    • /
    • 2016
  • Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.