• Asia Pacific Journal of Corpus Research
• /
• v.2 no.2
• /
• 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.

• Asia Pacific Journal of Corpus Research
• /
• v.4 no.1
• /
• 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.

• Asia Pacific Journal of Corpus Research
• /
• v.4 no.1
• /
• 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.

• Asia Pacific Journal of Corpus Research
• /
• v.4 no.2
• /
• 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.

• Asia Pacific Journal of Corpus Research
• /
• v.1 no.2
• /
• 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
• /
• v.36 no.5
• /
• 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.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• 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.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.132-139
• /
• 2021

This corpus-driven research expounded the compilation of the most frequently occurring academic words in the domain of syntax and compared the extracted wordlist with Academic Word List(AWL) of Coxhead(2000) and General Service List(GSL) of West(1953) to examine their distribution and coverage within the syntax corpus. A specialized 546,074 token corpus, composed of widely used must-read syntax textbooks for English education majors, was loaded into and analyzed with AntWordProfiler 1.4.1. Under the parameter of lexical frequency, the analysis identified 288(50.5%) AWL word forms, appeared 16 times or more, as well as 218(38.2%) AWL items, occurred not exceeding 15 times. The analysis also indicated that the coverage of AWL and GSL accounted for 9.19% and 78.92% respectively and the combination of GSL and AWL amounted to 88.11% of all tokens. Given that AWL can be instrumental in serving broad disciplinary needs, this study highlighted the necessity to compile the domain-specific AWL as a lexical repertoire to promote academic literacy and competence.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.3
• /
• pp.64-70
• /
• 2004

Korean and Japanese have same structure of sentences because they belong to same family of languages. So, The transfer driven machine translation is most efficient to translate each other. This paper introduce a method which creates a transfer dictionary for Token Based Transfer Driven Koran-Japanese Machine Translation(TB-TDMT). If the transfer dictionaries are created well, we get rid of useless effort for traditional parsing by performing shallow parsing. The semi-parser makes the dependency tree which has minimum information needed output generating module. We constructed the transfer dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 900 utterances which are collected from travel planning domain. The success-ratio of our system is $92\%$ on restricted testing environment and $81\%$ on unrestricted testing environment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.4
• /
• pp.40-46
• /
• 1999

This paper introduce a Koran-Japanese machine translation system which is a module in the spoken language interpreting system It is implemented based on the TDMT(Transfre Driven Machine Translation). We define a new unit of translation so called TOKEN. The TOKEN-based translation method resolves nonstructural feature in Korean sentences and increases the quaity of translating results. In our system, we get rid of useless effort for traditional parsing by performing semi-parsing. The semi-parser makes the dependency tree which has minimum information needed generating module. We constructed the generation dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 600 utterances which is collected from travel planning domain The success-ratio of our system is 87% on restricted testing environment and 71% on unrestricted testing environment.