• 아시아태평양코퍼스연구
• /
• 제2권2호
• /
• pp.43-48
• /
• 2021

The aim of this study is to analyze the trends of corpus driven research in Korean education. For this purpose, a total of 14 papers was searched online with the keywords including Korean corpus and Korean education. The data was categorized into three: vocabulary education, grammar education and corpus data construction methods. The analysis results suggest that the number of corpus studies in the field of Korean education is not large enough but continues to increase, especially in the research on data construction tools. This suggests there is a significant demand in corpus driven studies in Korean education field.

• 아시아태평양코퍼스연구
• /
• 제4권1호
• /
• pp.25-42
• /
• 2023

The number of studies on data-driven learning (DDL) has increased in recent years, and DDL's overall effectiveness as an L2 (second language) teaching methodology has been reported to be high. However, the degree of its effectiveness in grammar instruction, particularly for the goal of correcting errors in L2 writing, is still unclear. To provide guidelines for focused grammar instruction with DDL in the Japanese classroom setting, we aimed to identify the typical grammatical errors made by Japanese learners in the Cambridge Learner Corpus First Certificate in English (CLC FCE) dataset. The results revealed that three error types (nouns, articles, and prepositions) should be addressed in DDL grammar instruction for Japanese English as a foreign language (EFL) learners. In light of the findings, pedagogical implications and suggestions for future DDL research and practice are discussed.

• 아시아태평양코퍼스연구
• /
• 제4권1호
• /
• pp.61-71
• /
• 2023

This study examines the effects of data-driven learning (DDL)-an approach employing corpora for inductive language pattern learning-on error identification in second language (L2) writing. The data consists of error identification instances from fifty-five participants, compared across different reference materials: the Corpus of Contemporary American English (COCA), dictionaries, and no use of reference materials. There are three significant findings. First, the use of COCA effectively identified collocational and form-related errors due to inductive inference drawn from multiple example sentences. Secondly, dictionaries were beneficial for identifying lexical errors, where providing meaning information was helpful. Finally, the participants often employed a strategic approach, identifying many simple errors without reference materials. However, while maximizing error identification, this strategy also led to mislabeling correct expressions as errors. The author has concluded that the strategic selection of reference materials can significantly enhance the effectiveness of error identification in L2 writing. The use of a corpus offers advantages such as easy access to target phrases and frequency information-features especially useful given that most errors were collocational and form-related. The findings suggest that teachers should guide learners to effectively use appropriate reference materials to identify errors based on error types.

• 아시아태평양코퍼스연구
• /
• 제4권2호
• /
• pp.41-55
• /
• 2023

In data-driven learning (DDL), learners explore a corpus to understand vocabulary and grammar. Although many studies have emphasized the role of DDL in second language (L2) acquisition, L2 light verbs have been largely under-explored. To bridge this gap, this study focused on the learning outcomes of L2 light verbs among 29 intermediate-level Japanese university students. The research zeroed in on six prevalent light verbs in English: "make," "do," "take," "have," "give," and "get." Over nine weeks, the participants engaged with verb-noun collocations using worksheets that juxtaposed Japanese translations of the target collocations with their English equivalents, with the verbs omitted. With the aid of Wordbanks Online, they filled in the blanks and constructed accurate sentences. Before this activity, a 20-minute tutorial was given to the participants on how to interpret the concordance lines. The effectiveness of the DDL method was evaluated using pre-tests, immediate post-tests, and delayed post-tests. The results showed that DDL significantly improved the participants' knowledge of the target collocations of light verbs and nouns; the post-test and delayed post-test scores were significantly higher than the pre-test scores. The results showed that, overall, DDL contributed to memorizing the collocations of light verbs and nouns; however, DDL had different effects on the memorization of collocations across different light verbs. The extent of work on the worksheet is not the only factor in its retention, and observing concordance lines may promote learners' memorization of light-verb collocations.

• 아시아태평양코퍼스연구
• /
• 제1권2호
• /
• pp.57-72
• /
• 2020

This study seeks to add to the current understanding of learners' use of modality in argumentative writing. A learner corpus of argumentative essays on four topics was created and compared to native English speaker data from the International Corpus Network of Asian Learners of English (ICNALE). The relationship between learners' use of modal devices (MDs) and the devices' appearance in the school's curriculum was also examined. The results showed that learners relied on a very narrow range of MDs compared to those in previous studies. The frequency of use of MDs varied based on the topic and did not seem to be driven by cultural factors as has been previously suggested. Learners used more hedges than boosters on all topics, contradicting most previous studies. Curriculum was determined to have a direct correlation with MD use, and other important factors may include perception of topic and overreliance on certain MDs over others (the One-to-One principal). This research implies that learners' perception of topic should be explored further as a variable affecting MD use. Curricula should be designed based on frequency of MD use by English native speakers, and learners should receive instruction that teaches the norms of MD use in academic writing. The methodology used in the study to determine correlations between MD use and the curriculum has a wide range of potential applications in the field of Contrastive Interlanguage Analysis.

• ETRI Journal
• /
• 제36권5호
• /
• pp.714-720
• /
• 2014

In this paper, we propose the use of data-driven probabilistic utterance-level decision logic to improve Weighted Finite State Transducer (WFST)-based endpoint detection. In general, endpoint detection is dealt with using two cascaded decision processes. The first process is frame-level speech/non-speech classification based on statistical hypothesis testing, and the second process is a heuristic-knowledge-based utterance-level speech boundary decision. To handle these two processes within a unified framework, we propose a WFST-based approach. However, a WFST-based approach has the same limitations as conventional approaches in that the utterance-level decision is based on heuristic knowledge and the decision parameters are tuned sequentially. Therefore, to obtain decision knowledge from a speech corpus and optimize the parameters at the same time, we propose the use of data-driven probabilistic utterance-level decision logic. The proposed method reduces the average detection failure rate by about 14% for various noisy-speech corpora collected for an endpoint detection evaluation.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.285-292
• /
• 2007

The parallel corpus is an important resource in the research field of data-driven natural language processing, but there are only a few parallel corpora publicly available nowadays, mostly due to the high labor force needed to construct this kind of resource. A novel strategy is brought out to automatically fetch parallel text from the web in this paper, which may help to solve the problem of the lack of parallel corpora with high quality. The system we develop first downloads the web pages from certain hosts. Then candidate parallel page pairs are prepared from the page set based on the outer features of the web pages. The candidate page pairs are evaluated in the last step in which the sentences in the candidate web page pairs are extracted and aligned first, and then the similarity of the two web pages is evaluate based on the similarities of the aligned sentences. The experiments towards a multilingual web site show the satisfactory performance of the system.

• 한국콘텐츠학회논문지
• /
• 제21권12호
• /
• pp.132-139
• /
• 2021

본 코퍼스 기반 연구는 통사론 영역에서 자주 등장하는 학술어휘들을 목록화하고 추출된 단어 목록을 Coxhead(2000)의 학술어휘 목록(AWL) 및 West(1953)의 기본어휘 목록(GSL)과 비교하여 통사론 코퍼스 내의 어휘 분포와 범위를 조사하였다. 이를 위해 영어교육 전공자들이 주로 사용하는 필수 통사론 전공 서적을 546,074 단어 수준의 전문 코퍼스로 구축한 다음 AntWordProfiler 1.4.1로 분석하였다. 빈도를 기준으로 분석한 결과 16회 이상 등장한 학술어휘는 288개(50.5%), 15회 이하 등장한 학술어휘는 218개(38.2%)로 나타났다. AWL과 GSL의 출현 범위는 각각 9.19%와 78.92%로 나타났으며 GSL과 AWL을 포함한 비중은 전체 토큰의 88.11%에 달하였다. AWL이 광범위한 학술 요구를 충족시키는데 중추적인 역할을 할 수 있다는 점을 감안할 때, 본 연구는 학문 문식성과 학업 능력을 향상시키기 위한 방안으로 학문 분야별 학술 어휘목록을 편성할 필요가 있음을 강조하였다.

• 한국산업정보학회논문지
• /
• 제9권3호
• /
• pp.64-70
• /
• 2004

한국어와 일본어는 동일한 어족에 속하며 비슷한 문장구조를 가지고 있어 변환중심 기계번역 방법이 효율적이다. 본 논문에서는 토큰 단위의 변환중심 한일 기계번역 시스템을 위한 변환 사전을 생성하는 방법에 관하여 기술하였다. 변환 사전이 잘 구성되면 구문분석 단계에서는 대역어를 선정하기에 적합한 정도까지의 의존트리를 생성하는 간이 파싱 만을 함으로써 필요 없는 노력을 경감시킬 수 있다. 게다가 구문해석 시에 최종의 결과 트리를 만들지 않아도 되므로 문어체 문장은 물론 입력 형태가 비정형적인 대화체 문장에서 더욱 큰 효과를 볼 수 있다. 본 논문의 변환 사전은 한국전자통신 연구원이 수집한 음성 데이터베이스로부터 추출한 말뭉치를 사용해 구성하였다. 구현한 시스템은 여행 계획영역에서 수집된 900여 발화 안의 문장을 대상으로 시험하였는데 제한된 환경에서 $92\%$, 아무런 제약이 없는 환경에서는 $81\%$의 성공률을 보였다.

• 한국산업정보학회논문지
• /
• 제4권4호
• /
• pp.40-46
• /
• 1999

본 논문에서는 음성언어 자동 통역시스템의 일부 모듈로 구현한 한일 기계번역 시스템을 소개하였다. 이 번역시스템은 예제중심 기계번역(EBMT)에 기초를 둔 변환중심 기계번역(TDMT) 방법을 기반으로 구현하였다. 본 시스템에서는 토큰(TOKEN)이라는 새로운 번역단위를 정의하여 사용하였다. 토큰단위의 번역방법을 사용함으로써 한국어 문장의 매우 비 정형적인 점을 해결하고 번역의 질을 높일 수 있다. 본 시스템의 구문분석 단계에서는 대역어를 선정하기에 적합한 정도까지의 의존트리를 생성하는 간이파싱만을 함으로써 필요없는 노력을 경감시켰다. 대역어 사전은 한국전자통신 연구원이 수집한 음성 데이터베이스로부터 추출한 말뭉치를 사용해 구성하였다. 구현한 시스템은 여행 계획영역에서 수집된 600 발화 안의 문장을 대상으로 시험하였는데 제한된 환경에서 87%, 아무런 제약이 없는 환경에서는 71%의 성공률을 보였다.