• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.74-80
• /
• 2002

There are many researches on post-processing methods for the Korean continuous speech recognition enhancement using natural language processing techniques. It is very difficult to use a formal morphological analyzer for improving the speech recognition because the analysis technique of natural language processing is mainly for formal written languages. In this paper, we propose a speech recognition enhancement model using syntactic unit of morphemes. This approach uses the functional word level longest match which dose not consider spacing words. We describe the post-processing mechanism for the improving speech recognition by using proposed model which uses the relationship of phonological structure information between predicates md auxiliary predicates or bound nouns that are frequently occurred in Korean sentences.

• MALSORI
• /
• no.56
• /
• pp.127-134
• /
• 2005

Although the narrative development and the acquisition of the Korean grammatical morphemes by monolingual Korean-speaking children have been studied extensively, little is known about the narrative characteristics and the processes through which native speakers of other languages (L2 speakers) use the Korean grammatical morphemes. To understand the similarities and differences between L1 and L2 narrative skills and Korean grammatical morpheme use, 13 native Chinese-speaking college students who are learning Korean as a second language were studied. L2 participants used significantly fewer words, subordinate clauses, connective morphological endings, and pronouns per T-unit. Their speech also illustrated significantly more omission and confusion (substitution) errors in the use of auxiliary words and verb endings. Some of the syntactic and morphological factors need to be considered for the intervention of speakers with limited Korean proficiency.

• Proceedings of the KSPS conference
• /
• 2000.07a
• /
• pp.47-58
• /
• 2000

For the learners of English as a foreign language, oral repetition of model sentences is an e essential practice to improve their listening and speaking abilities of English. Skill training of both speech perception and production is involved in this practice. This paper reports on an observation of production e$\pi$ors in such practice made by Japanese college students in my class. The teaching material used is intended for acquainting the learners with basic English rhythm and intonation p patterns. The students were required to repeat each sentence in a series of conversations after a model reading. Although the vocabulary and expressions were rather limited, I monitored different kinds of errors in their repetition. Putting aside intonation, their difficulties are classified into five types; 1. Omission of words or morphemes, 2. Addition of unnecessary words or morphemes, 3. Replacement of words, 4. Japanization of English sounds, 5. Wrong rhythm caused by improper stress assignment. Accurate listening, especially to weakly stressed syllables and to assimilated sounds, as has often been pointed out, is the most difficult part in perception for them. Japanese sound system interferes in production of English sounds. More often than not their knowledge of grammar or the context does not work at all to guess the words they are hearing

• Journal of Korea Multimedia Society
• /
• v.16 no.3
• /
• pp.366-374
• /
• 2013

One of the most important problems in syntactic analysis is syntactic ambiguities. This paper proposes a parsing system and this system can reduce syntactic ambiguities by using segmentation method and argument information method. The proposed system uses morphemes for the input of syntax analysis system, and syntactic analysis system generates all possible parse trees from the given morphemes. Therefore, this system generates many syntactic ambiguity problems. We use three methods to solve these problems. First is disambiguation method in morphological analysis, second is segmentation method in syntactic analysis processing, and the last method is using argument information. Using these three methods, we can reduce many ambiguities in Korean syntactic analysis. In our experiment, our approach decreases about 53% of syntactic ambiguities.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.396-404
• /
• 1998

본 논문에서는 언어학적 단위인 형태소의 특성을 유지하면서 음성인식 과정에 적합한 분리 기준의 새로운 디코딩 단위인 의사형태소(Pseudo-Morpheme)를 정의 하였다. 이러한 필요성을 확인하기 위해 새로이 정의된 40개의 품사 태그를 갖는 의사 형태소를 표제어 단위로 삼아 발음사전 생성과 형태소 해석에 초점을 두고 한국어 연속음성 인식 시스템을 구성하였다.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.123-128
• /
• 1996

So far we have proposed the following constraint ranking for the (over-)application of the coda neutralization: (22) License family ≫ UE family ≫ IDENT-IO family ≫ Base-ID This analysis shows that only the surface level is enough to analyze the opaque behaviors of coda neutralization. Uniform Exponence constraint is worth further study since it can handle Consonant Cluster Simplification and underapplication of /t/-palatalization in Korean compounds in which morphemes before a stem are uniformly realized as one surface form: i.e., the output base form (S. Hong in preparation)(equation omitted)

• Speech Sciences
• /
• v.9 no.2
• /
• pp.49-58
• /
• 2002

This study is to classify intonation types of sentence terminal in accordance with sentence form in Korean dialects. Intonation types of sentence terminal in declarative, interrogative (yes-no and wh-sentence), imperative, suggestive of Gyeongnam dialect are low fall, high fall, high fall, low fall, so are not distinctive by intonation, but distinctive by final ending morphemes. But those of Jungbu dialect are low fall, rise-fall and full rise, high level, low rise-fall. Those of Jeonnam dialect are low level, rise-fall and full rise, high level, high level. So those of Jungbu dialect are similar to Jeonnam dialect.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.53-58
• /
• 2015

본 연구는 한국어 정보처리를 위한 형태소 연구 중 선어말어미 분석과 합성을 위한 처리 모형을 제안한다. 이를 위해 (1) 어미를 정의하고 선정한 뒤 (2) 낱말 패러다임 형태 이론에 기반하여 동사 어간을 그 특징에 따라 적절하게 분류한다. (3) 또한 형태소 결합을 위해 필요한 조작들을 기술하고 (4) 마지막으로 어미의 결합 순서와 결합 제약을 만족시킬 규칙을 만들어 제시함으로써 각 조작과 규칙을 이용하여 기계 분석을 하기 위한 프로그램 모형을 내놓는다.

• Journal of Korean Academy of Nursing
• /
• v.44 no.3
• /
• pp.328-338
• /
• 2014

Purpose: This study was done to explore experiences of persons living through the periods of cancer diagnosis, treatment, and self-care. Methods: With permission, texts of 29 cancer survival narratives (8 men and 21 women, winners in contests sponsored by two institutes), were analyzed using Kang's Korean-Computerized-Text-Analysis-Program where the commonly used Korean-Morphological-Analyzer and the 21st-century-Sejong-Modern-Korean-Corpora representing laymen's Korean-language-use are connected. Experiences were explored based on words included in 100 highly-used-morphemes. For interpretation, we used 'categorizing words by meaning', 'comparing use-rate by periods and to the 21st-century-Sejong-Modern-Korean-Corpora', and highly-used-morphemes that appeared only in a specific period. Results: The most highly-used-word-morpheme was first-person-pronouns followed by, diagnosis treatment-related- words, mind-expression-words, cancer, persons-in-meaningful-interaction, living and eating, information-related-verbs, emotion-expression- words, with 240 to 0.8 times for layman use-rate. 'Diagnosis-process', 'cancer-thought', 'things-to-come-after-diagnosis', 'physician husband', 'result-related-information', 'meaningful-things before diagnosis-period', and 'locus-of-cause' dominated the life of the diagnosis-period. 'Treatment', 'unreliable-body', 'husband people mother physician', 'treatment-related-uncertainty', 'hard-time', and 'waiting-time represented experiences in the treatment-period. Themes of living in the self-care-period were complex and included 'living-as-a-human', 'self-managing-of-diseased-body', 'positive-emotion', and 'connecting past present future'. Conclusion: The results show that the experience of living for persons with cancer is influenced by each period's own situational-characteristics. Experiences of the diagnosis and treatment-period are negative disease-oriented while that of the self-care period is positive present-oriented.