• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.273-279
• /
• 2018

This study aimed at providing a comprehensive account of the sources and causes of errors in business emails that Korean college students wrote using a translation machine. Data were collected from 21 emails written by the students who took a business English course. Findings indicated that the students tended to make frequent errors in verb use and verb tense as well as a definite article, countable/noncountable nouns, time adverbs and prepositions. Therefore, the study suggested that the students' common errors imply that they experience some difficulties learning these linguistic features. Given that learners' errors can give us valuable insights into teaching and learning how to write in English, pedagogical suggestions are put forward based on the study results.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.67-70
• /
• 2019

상호참조해결은 자연언어 문서 내에서 같은 개체를 나타내는 언급들을 연결하는 문제다. 대명사, 지시 관형사, 축약어, 동음이의어와 같은 언급들의 상호참조를 해결함으로써, 다양한 자연언어 처리 문제의 성능 향상에 기여할 수 있다. 본 논문에서는 현재 영어권 상호참조해결에서 좋은 성능을 내고 있는 BERT 기반 상호참조해결 모델에 한국어 데이터 셋를 적용시키고 표층형을 이용한 규칙을 추가했다. 본 논문의 모델과 기존의 모델들을 실험하여 성능을 비교하였다. 기존의 연구들과는 다르게 적은 특질로 정밀도 73.59%, 재현율 71.1%, CoNLL F1-score 72.31%의 성능을 보였다. 모델들의 결과를 분석하여 BERT 기반의 모델이 다양한 특질을 사용한 기존 딥러닝 모델에 비해 문맥적 요소를 잘 파악하는 것을 확인했다.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.2
• /
• pp.427-436
• /
• 2021

The purpose of this study is to implement a machine learning language model that learns literary texts. Literary texts have an important characteristic that pairs of question-and-answer are not frequently clearly distinguished. Also, literary texts consist of pronouns, figurative expressions, soliloquies, etc. They hinder the necessity of machine learning using literary texts by making it difficult to learn algorithms. Algorithms that learn literary texts can show more human-friendly interactions than algorithms that learn general sentences. For this goal, this paper proposes three text correction tasks that must be preceded in researches using literary texts for machine learning language model: pronoun processing, dialogue pair expansion, and data amplification. Learning data for artificial intelligence should have clear meanings to facilitate machine learning and to ensure high effectiveness. The introduction of special genres of texts such as literature into natural language processing research is expected not only to expand the learning area of machine learning, but to show a new language learning method.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.53-64
• /
• 2007

This paper attempts to verify the theoretical claims in Syntax ($Bo{\check{s}}kovi{\acute{c}}$ & Lasnik, 2003; Kim, 1999, 2004) about the phrasing in English that-clauses, presenting an acoustic experiment conducted to observe the patterns of edge tones at the boundaries of that. In the experiment, two different that clauses, complement and relative clauses, were varied in forms (that-retention, that-deletion, adverb insertion before that) and length. Results showed that edge tones, if occurred, mostly showed up before the complement clauses in that-deletion sentences (67%), and that their positions polarized in adverb insertion sentences (56% before toot and 44% after toot). In the relative clauses, phrasing mostly occurred before toot as opposed to after toot in that-retention (73%) and adverb insertion sentences (87%). Additionally, phrasing tends to occur more frequently as the sentences get longer. The results suggest that the previous claims based on syntax are not consistent with the results of the current phonetic experiment. This may be interpreted as stating that syntactic boundaries do not always indicate phonetic phrasing, and that there may be some other factors to determine phrasing patterns, for example, rhythmic phrasing operating at the surface level of speech.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.213-219
• /
• 2023

The purpose of this study is to prove the students' understanding of audiovisual translation and the class effect by using the lesson plan that can efficiently teach the audiovisual translation class, which is one of the major elective courses at S University. After taking the course, a questionnaire was surveyed and the results were analyzed. The response and satisfaction with the content of the class was positive and very high, and it was confirmed that the background knowledge of the movie was especially helpful for translation practice. The effect of the class was focused on translating subtitles, and only the abbreviated part of the response to the questionnaire was expressed in a table, and the rest was expressed descriptively. Specifically, the response rate for abbreviations, pronouns, titles suitable for personal relationships, putting subjects and predicates close together were the most positive, followed by natural expressions, sign writing, handling of honorifics and informal words, attaching subject and predicates closer, translating them in reverse, and converting units.

• Phonetics and Speech Sciences
• /
• v.13 no.2
• /
• pp.27-35
• /
• 2021

This study investigated the status of the wh-island constraint in Seoul Korean. The syntactic movement of a wh-phrase out of an embedded sentence so as to have wide scope at LF is known to be invalid as it violates the wh-island constraint, but there have been studies in which such a movement was possible when the sentence is read with a wh-intonation. We conducted perceptual tests in which subjects were asked to select an answer after listening to each of the four types of interrogative sentences. Three of them were with 'Nugu-leul', which is an accusative form of the wh-phrase 'who' as well as an indefinite form. The fourth sentence contained the name of a person. 'Nugu-leul' and the noun were positioned in the same embedded sentence to see whether the subjects accepted a matrix scope interpretation of the wh-phrases. Response time was transformed to normalized log response time and checked to find any differences in the time taken to select the answers depending on different types of interrogative sentences. The results showed the subjects had a definite preference for the matrix scope interpretation for the sentences with a wh-intonation. The response time required to select the matrix scope interpretation was longer than for any other type of interrogative sentence. We concluded that the wh-island constraint in Seoul Korean is weak.