http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
학습자 코퍼스를 이용한 영어 전치사 오류 교정 모델 개발
한나래(Na-Rae Han),이수화(Soo-Hwa Lee) 사단법인 한국언어학회 2009 언어학 Vol.0 No.53
With growing demands for computerized tools in ESL (English as a Second Language) and EFL (English as a Foreign Language) classrooms, applying latest advancement in natural language processing to developing models for diagnosing and correcting errors in learner language poses an interesting research question which touches on issues of diverse nature: engineeringoriented, theoretical and also practical. In this study, we present a method of statistically modeling preposition usage errors by training a classifier exclusively on an error-annotated corpus of L2 essays. The data set, Chungdahm English Learner Corpus, is a large-scale corpus containing over 130 million words and over 860,000 individual essays, written by middle school students whose native language is Korean. We train a maximum entropy classifier on the preposition instances in the corpus based on a small number of simplistic contextual features and report a good level of performance at over 90% precision and 29% recall in identifying and error and suggesting a grammatical alternative. In comparison with the more widely practiced method of building language correction models based on well-formed texts produced by native users of the language, the approach presented in this study invites some interesting theoretical and empirical considerations, namely the nature of the resultant model as one of a particular sub-language, the English of Korean middle students in this case, and also its extendability to other variations of the English language.
한나래(Na-Rae Han) 한국인지과학회 2009 인지과학 Vol.20 No.2
본고에서는 빈도 정보를 이용한 저자 판별 (authorship attribution) 기법을 한국어에 적용한 연구를 소개한다. 그 대상으로는 정형화된 장르인 신문 칼럼을, 구체적으로는 조선일보에 연재 중인 4인 칼럼니스트들의 각 40개 칼럼, 총 160개 칼럼 텍스트를 선정하였다. 이들에 대하여 어절, 음절, 형태소, 각 단위 2연쇄 등의 다양한 언어 단위들의 빈도 정보들을 이용한 저자 판별을 시도한 결과, 형태소 빈도를 기반으로 하여 최고 93%를 넘는 높은 예측 정확도를 얻을 수 있었다. 또한, 저자 개인 문체간의 거리도 빈도 정보로써 계량적 표상이 가능함을 보일 수 있었다. 이로써 빈도 분석과 같은 통계적, 계량적 방법을 통하여 한국어 텍스트에 대한 성공적인 저자 판별과 개인 문체의 정량화가 가능하다는 결론을 내릴 수 있다. This paper presents an authorship attribution study in Korean conducted on a corpus of newspaper column texts. Based on the data set consisting of a total of 160 columns written by four columnists of Chosun Daily, the approach utilizes relative frequencies of various lexical units in Korean such as fully inflected words, morphemes, syllables and their bigrams in an attempt to establish authorship of a blind text selected from the set. Among these various lexical units, "the morpheme" is found to be most effective in predicting who among the four potential candidates authored a text, reporting accuracies of over 93%. The results indicate that quantitative and statistical techniques in authorship attribution and computational stylistics can be successfully applied to Korean texts.
국내 소재 글로벌 제약사의 연구개발 규모 및 현황 : 2016~2020년 5년 간 설문조사
오인선(In-Sun Oh),조혜원(Hye Won Cho),이현주(Hyun Joo Lee),송혜원(Hye Won Song),한나래(Na Rae Han),김초롱(Cho Rong Kim),임혜인(Hye In Lim),신주영(Ju-Young Shin) 대한약학회 2021 약학회지 Vol.65 No.6
While the importance of the global pharmaceutical industry is growing owing to continued new drug developments and R&D investments, the scale of global pharmaceutical companies in Korea remains unclear. We therefore investigated the R&D status of global pharmaceutical companies in Korea through an annual survey from 2016 to 2020. We assessed five factors annually and their trend over the 5-year period: costs, personnel, number of clinical trials, number of clinical trial subjects, and others. We then examined the correlation among factors and further compared the trend between each factor and the gross domestic product (GDP). Of 35 companies that responded, 25 responded for five consecutive years and showed a steady increase in the cost, personnel, and the number of clinical trials. While costs and personnel increased more than the GDP over the 5-year period, the number of clinical trials remained similar; number of clinical trial subjects highly fluctuated year-by-year. Moreover, a high correlation was found for cost and personnel (r>0.8852), and cost and the number of clinical trials (r>0.8452). In conclusion, costs, personnel, and the number of clinical trials of global pharmaceutical companies in Korea steadily increased from 2016 to 2020 and thus, have continuously contributed to the domestic economy.