• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.199-208
• /
• 2022

Korean is an agglutinative language, and one or more morphemes are combined to form a single word. Part-of-speech tagging method separates each morpheme from a word and attaches a part-of-speech tag. In this study, we propose a new Korean part-of-speech tagging method based on the Head-Tail tokenization technique that divides a word into a lexical morpheme part and a grammatical morpheme part without decomposing compound words. In this method, the Head-Tail is divided by the syllable boundary without restoring irregular deformation or abbreviated syllables. Korean part-of-speech tagger was implemented using the Head-Tail tokenization and deep learning technique. In order to solve the problem that a large number of complex tags are generated due to the segmented tags and the tagging accuracy is low, we reduced the number of tags to a complex tag composed of large classification tags, and as a result, we improved the tagging accuracy. The performance of the Head-Tail part-of-speech tagger was experimented by using BERT, syllable bigram, and subword bigram embedding, and both syllable bigram and subword bigram embedding showed improvement in performance compared to general BERT. Part-of-speech tagging was performed by integrating the Head-Tail tokenization model and the simplified part-of-speech tagging model, achieving 98.99% word unit accuracy and 99.08% token unit accuracy. As a result of the experiment, it was found that the performance of part-of-speech tagging improved when the maximum token length was limited to twice the number of words.

• Journal of KIISE:Software and Applications
• /
• v.41 no.7
• /
• pp.523-532
• /
• 2014

In this paper, we propose a lattice-based discriminative approach for Korean morphological analysis and POS tagging. In our approach, for an input sentence, a morpheme lattice is first created from a lexicon where each node corresponds to a morpheme in the lexicon and each edge is formed between two consecutive morphemes. A candidate result of morphological analysis is then represented as a path in the morpheme lattice which is defined as the sequence of edges, starting in the initial state and ending with the final state. In this setting, the morphological analysis is simply considered as the process of finding the best path among all possible paths. Experiment results show that the proposed lattice-based method outperforms the first-order linear-chain CRF.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.501-506
• /
• 2008

Statistical POS tagging is prone to error, because of the inherent limitations of statistical data, especially single source of data. Therefore it is widely agreed that the possibility of further enhancement lies in exploiting various knowledge sources. However these data sources are bound to be inconsistent to each other. This paper shows the possibility of using maximum entropy model to Korean language POS tagging. We use as the knowledge sources n-gram data and trigger pair data. We show how perplexity measure varies when two knowledge sources are combined using maximum entropy method. The experiment used a trigram model which produced 94.9% accuracy using Hidden Markov Model, and showed increase to 95.6% when combined with trigger pair data using Maximum Entropy method. This clearly shows possibility of further enhancement when various knowledge sources are developed and combined using ME method.

• KIISE Transactions on Computing Practices
• /
• v.22 no.7
• /
• pp.315-319
• /
• 2016

Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.3-8
• /
• 2016

형태소 분석기는 많은 자연어 처리 영역에서 필수적인 언어 도구로 활용되기 때문에 형태소에 대한 품사를 결정하는 것은 매우 중요하다. 최근 음절 기반으로 형태소의 품사를 태깅하는 방법에 대한 연구들이 많이 진행되고 있다. 음절 단위 형태소 분석은 음절 단위로 분리된 형태소에 대해서 기계학습을 이용하여 분리된 음절 단위로 품사를 태깅하는 단계를 가진다. 본 논문에서는 기존의 CRF를 이용한 음절 단위 품사 태깅 방법을 개선하기 위해 bi-LSTM-CRFs를 이용한 방법을 제안한다. 또한, bi-LSTM-CRFs의 입력을 음절의 품사 분포 벡터를 이용해 확장함으로써 음절 단위 품사 태깅의 성능을 향상 시켰다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.3-8
• /
• 2016

형태소 분석기는 많은 자연어 처리 영역에서 필수적인 언어 도구로 활용되기 때문에 형태소에 대한 품사를 결정하는 것은 매우 중요하다. 최근 음절 기반으로 형태소의 품사를 태깅하는 방법에 대한 연구들이 많이 진행되고 있다. 음절 단위 형태소 분석은 음절 단위로 분리된 형태소에 대해서 기계학습을 이용하여 분리된 음절 단위로 품사를 태깅하는 단계를 가진다. 본 논문에서는 기존의 CRF를 이용한 음절 단위 품사 태깅 방법을 개선하기 위해 bi-LSTM-CRFs를 이용한 방법을 제안한다. 또한, bi-LSTM-CRFs의 입력을 음절의 품사 분포 벡터를 이용해 확장함으로써 음절 단위 품사 태깅의 성능을 향상 시켰다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1639-1658
• /
• 2019

Named entity recognition (NER) is an important technique for improving the performance of data mining and big data analytics. In previous studies, NER systems have been employed to identify named-entities using statistical methods based on prior information or linguistic features; however, such methods are limited in that they are unable to recognize unregistered or unlearned objects. In this paper, a method is proposed to extract objects, such as technologies, theories, or person names, by analyzing the collocation relationship between certain words that simultaneously appear around specific words in the abstracts of academic journals. The method is executed as follows. First, the data is preprocessed using data cleaning and sentence detection to separate the text into single sentences. Then, part-of-speech (POS) tagging is applied to the individual sentences. After this, the appearance and collocation information of the other POS tags is analyzed, excluding the entity candidates, such as nouns. Finally, an entity recognition model is created based on analyzing and classifying the information in the sentences.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.544-547
• /
• 2021

한국어의 품사 태깅 문제는 입력 어절의 형태소 분석 후보들로부터 통계적으로 적절한 품사 태그를 가지는 후보들을 찾는 방식으로 해결하여 왔다. 어절을 형태소 단위로 분리하고 품사를 부착하는 기존의 방식은 품사태그 정보를 딥러닝 feature로 사용할 때 문장의 의미를 이해하는데 복잡도를 증가시키는 요인이 된다. 본 연구에서는 품사 태깅 문제를 단순화 하여 한 어절을 Head와 Tail이라는 두 가지 유형의 형태소 토큰으로 분리하여 Head와 Tail에 대해 품사를 부착한다. Head-Tail 품사 태깅 방법을 Sequence-to-Sequence 문제로 정의하여 Transformer를 이용한 Head-Tail 품사 태거를 설계하고 구현하였다. 학습데이터로는 KCC150 말뭉치의 품사 태깅 말뭉치 중에서 788만 문장을 사용하고, 실험 데이터로는 10만 문장을 사용하였다. 실험 결과로 토큰 정확도는 99.75%, 태그 정확도는 99.39%, 토큰-태그 정확도는 99.31%로 나타났다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.19-21
• /
• 2006

본 논문에서는 의료임상 문서의 구절(phrase)를 대상으로 고차원 개념의 정보를 태깅하는 시맨틱 태깅 시스템을 제안하고 있다. 시스템은 의사들이 기록한 임상 기록으로부터 정보를 추출한다. 태깅은 UMLS와 POS, 약어 태깅이 된 문서를 대상으로 HMM 모델에 의거하여 이루어지게 된다. 태깅된 결과는 의료 상에서의 경험적 지식을 추출하는데 이용되어 의사들의 의사 결정을 지원하게 된다.