• Journal of Industrial Convergence
• /
• v.18 no.4
• /
• pp.93-99
• /
• 2020

The Journal of Industrial Management Society in Republic of Korea. In order to explore the effect of overseas language training on the development of foreign language accuracy, this study investigates the errors in English compositions produced by 27 Korean university students who received overseas language training for 15 weeks. For data collection, students were made to take two tests, a pretest and a posttest, a semester apart. The differences in composition elements and errors between the two tests were examined and statistical analyses were performed. Results showed that while the average length of the compositions and sentences increased, the number of sentences decreased in the posttest. Also, more errors were found in the posttest where the students tried to construct more complex sentence structures. The students' ability to generate sentences were found to have improved, while their competence in using grammatical elements accurately within sentences did not see great improvement. This implies that overseas language training was not effective for aiding the development of one's grammatical accuracy of a foreign language over a 15-week period for the students.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.15-23
• /
• 2022

In the field of patents, as NLP(Natural Language Processing) is a challenging task due to the linguistic specificity of patent literature, there is an urgent need to research a language model optimized for Korean patent literature. Recently, in the field of NLP, there have been continuous attempts to establish a pre-trained language model for specific domains to improve performance in various tasks of related fields. Among them, ELECTRA is a pre-trained language model by Google using a new method called RTD(Replaced Token Detection), after BERT, for increasing training efficiency. The purpose of this paper is to propose KorPatELECTRA pre-trained on a large amount of Korean patent literature data. In addition, optimal pre-training was conducted by preprocessing the training corpus according to the characteristics of the patent literature and applying patent vocabulary and tokenizer. In order to confirm the performance, KorPatELECTRA was tested for NER(Named Entity Recognition), MRC(Machine Reading Comprehension), and patent classification tasks using actual patent data, and the most excellent performance was verified in all the three tasks compared to comparative general-purpose language models.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.77-89
• /
• 2022

It has been proven through many previous researches that the pretrained language model with a large corpus helps improve performance in various natural language processing tasks. However, there is a limit to building a large-capacity corpus for training in a language environment where resources are scarce. Using the Cross-lingual Post-Training (XPT) method, we analyze the method's efficiency in Korean, which is a low resource language. XPT selectively reuses the English pretrained language model parameters, which is a high resource and uses an adaptation layer to learn the relationship between the two languages. This confirmed that only a small amount of the target language dataset in the relationship extraction shows better performance than the target pretrained language model. In addition, we analyze the characteristics of each model on the Korean language model and the Korean multilingual model disclosed by domestic and foreign researchers and companies.

• Journal of Korean language education
• /
• v.28 no.1
• /
• pp.141-171
• /
• 2017

This study investigates Korean language teachers' perception/beliefs and practices in written feedback. Two types of data were collected: (1) teachers' feedback on three compositions by elementary-level learners, and (2) a survey questionnaire. The result showed that teachers perceived written feedback to be important even though they had not enough opportunities to receive appropriate training. Lack of training brought about limited feedback in terms of both quantity and quality, and inconsistency between their beliefs and practice. This study closes with the needs for teacher training and further studies on teachers' feedback practices.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2010.05a
• /
• pp.60-65
• /
• 2010

Language learning involves linguistic environments around the learner. So the variation in training input to which the learner is exposed has been linked to their language learning. We explore how linguistic experiences can cause differences in learning linguistic structural features, as investigate in a probabilistic graphical model. We manipulate the amounts of training input, composed of natural linguistic data from animation videos for children, from holistic (one-word expression) to compositional (two- to six-word one) gradually. The recognition and generation of sentences are a "probabilistic" constraint satisfaction process which is based on massively parallel DNA chemistry. Random sentence generation tasks succeed when networks begin with limited sentential lengths and vocabulary sizes and gradually expand with larger ones, like children's cognitive development in learning. This model supports the suggestion that variations in early linguistic environments with developmental steps may be useful for facilitating language acquisition.

• Journal of the Korean Society for Library and Information Science
• /
• v.43 no.1
• /
• pp.313-332
• /
• 2009

Cross-language text categorization(CLTC) can classify documents automatically using training set from other language. In this study, collections appropriated for CLTC were extracted from KTSET. Classification performance of various CLTC methods were compared by SVM classifier using machine translation. Results showed that the classification performance in the order of poly-lingual training method, training-set translation and test-set translation. However, training-set translation could be regarded as the most useful method among CLTC, because it was efficient for machine translation and easily adapted to general environment. On the other hand, low performance was shown to be due to the feature reduction or features with no subject characteristics, which occurred in the process of machine translation of CLTC.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.217-220
• /
• 2007

This study outlines a small-sized dialog style ETRI Korean TTS system which applies a HMM based speech synthesis techniques. In order to build the VoiceFont, dialog-style 500 sentences were used in training HMM. And the context information about phonemes, syllables, words, phrases and sentence were extracted fully automatically to build context-dependent HMM. In training the acoustic model, acoustic features such as Mel-cepstrums, logF0 and its delta, delta-delta were used. The size of the VoiceFont which was built through the training is 0.93Mb. The developed HMM-based TTS system were installed on the ARM720T processor which operates 60MHz clocks/second. To reduce computation time, the MLSA inverse filtering module is implemented with Assembly language. The speed of the fully implemented system is the 1.73 times faster than real time.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.3-8
• /
• 2015

In this paper, we investigate an input dimension reduction method using continuous word vector in deep neural network language model. In the proposed method, continuous word vectors were generated by using Google's Word2Vec from a large training corpus to satisfy distributional hypothesis. 1-of-${\left|V\right|}$ coding discrete word vectors were replaced with their corresponding continuous word vectors. In our implementation, the input dimension was successfully reduced from 20,000 to 600 when a tri-gram language model is used with a vocabulary of 20,000 words. The total amount of time in training was reduced from 30 days to 14 days for Wall Street Journal training corpus (corpus length: 37M words).

• Speech Sciences
• /
• v.11 no.4
• /
• pp.43-52
• /
• 2004

Model parameters in HMM based speech recognition systems are normally estimated using Maximum Likelihood Estimation(MLE). The MLE method is based mainly on the principle of statistical data fitting in terms of increasing the HMM likelihood. The optimality of this training criterion is conditioned on the availability of infinite amount of training data and the correct choice of model. However, in practice, neither of these conditions is satisfied. In this paper, we propose a training algorithm, MCE(Minimum Classification Error), to improve the performance of a speech recognizer detecting mispronunciation of a foreign language. During the conventional MLE(Maximum Likelihood Estimation) training, the model parameters are adjusted to increase the likelihood of the word strings corresponding to the training utterances without taking account of the probability of other possible word strings. In contrast to MLE, the MCE training scheme takes account of possible competing word hypotheses and tries to reduce the probability of incorrect hypotheses. The discriminant training method using MCE shows better recognition results than the MLE method does.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.126-133
• /
• 2024

Large language models (LLMs) have revolutionized the global landscape of technology beyond natural language processing. Owing to their extensive pre-training on vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without additional fine-tuning. General-purpose chatbots based on LLMs can optimize the efficiency of radiologists in terms of their professional work and research endeavors. Importantly, these LLMs are on a trajectory of rapid evolution, wherein challenges such as "hallucination," high training cost, and efficiency issues are addressed, along with the inclusion of multimodal inputs. In this review, we aim to offer conceptual knowledge and actionable guidance to radiologists interested in utilizing LLMs through a succinct overview of the topic and a summary of radiology-specific aspects, from the beginning to potential future directions.