• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2419-2422
• /
• 2003

To improve performance of sentence speech recognition systems, we need to consider perplexity of language model and the number of words of dictionary for increasing vocabulary size. In this paper, we propose a language model of VCCV units for sentence speech recognition. For this, we choose VCCV units as a processing units of language model and compare it with clauses and morphemes. Clauses and morphemes have many vocabulary and high perplexity. But VCCV units have small lexicon size and limited vocabulary. An advantage of VCCV units is low perplexity. This paper made language model using bigram about given text. We calculated perplexity of each language processing unit. The perplexity of VCCV units is lower than morpheme and clause.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.29-35
• /
• 2020

In this paper, we propose a new structured entity recognition DeNERT model. Recently, the field of natural language processing has been actively researched using pre-trained language representation models with a large amount of corpus. In particular, the named entity recognition, which is one of the fields of natural language processing, uses a supervised learning method, which requires a large amount of training dataset and computation. Reinforcement learning is a method that learns through trial and error experience without initial data and is closer to the process of human learning than other machine learning methodologies and is not much applied to the field of natural language processing yet. It is often used in simulation environments such as Atari games and AlphaGo. BERT is a general-purpose language model developed by Google that is pre-trained on large corpus and computational quantities. Recently, it is a language model that shows high performance in the field of natural language processing research and shows high accuracy in many downstream tasks of natural language processing. In this paper, we propose a new named entity recognition DeNERT model using two deep learning models, DQN and BERT. The proposed model is trained by creating a learning environment of reinforcement learning model based on language expression which is the advantage of the general language model. The DeNERT model trained in this way is a faster inference time and higher performance model with a small amount of training dataset. Also, we validate the performance of our model's named entity recognition performance through experiments.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.11-29
• /
• 2022

Pre-trained language models are the most important and widely used tools in natural language processing tasks. Since those have been pre-trained for a large amount of corpus, high performance can be expected even with fine-tuning learning using a small number of data. Since the elements necessary for implementation, such as a pre-trained tokenizer and a deep learning model including pre-trained weights, are distributed together, the cost and period of natural language processing has been greatly reduced. Transformer variants are the most representative pre-trained language models that provide these advantages. Those are being actively used in other fields such as computer vision and audio applications. In order to make it easier for researchers to understand the pre-trained language model and apply it to natural language processing tasks, this paper describes the definition of the language model and the pre-learning language model, and discusses the development process of the pre-trained language model and especially representative Transformer variants.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2E
• /
• pp.51-55
• /
• 2004

In this paper, we propose a style-specific language model adaptation scheme using n-gram based tf*idf similarity for Korean spontaneous speech recognition. Korean spontaneous speech shows especially different style-specific characteristics such as filled pauses, word omission, and contraction, which are related to function words and depend on preceding or following words. To reflect these style-specific characteristics and overcome insufficient data for training language model, we estimate in-domain dependent n-gram model by relevance weighting of out-of-domain text data according to their n-. gram based tf*idf similarity, in which in-domain language model include disfluency model. Recognition results show that n-gram based tf*idf similarity weighting effectively reflects style difference.

• Journal of Information Technology Services
• /
• v.19 no.5
• /
• pp.83-91
• /
• 2020

Language Models such as BERT has been an important factor of deep learning-based natural language processing. Pre-training the transformer-based language models would be computationally expensive since they are consist of deep and broad architecture and layers using an attention mechanism and also require huge amount of data to train. Hence, it became mandatory to do fine-tuning large pre-trained language models which are trained by Google or some companies can afford the resources and cost. There are various techniques for fine tuning the language models and this paper examines three techniques, which are data augmentation, tuning the hyper paramters and partly re-constructing the neural networks. For data augmentation, we use no-answer augmentation and back-translation method. Also, some useful combinations of hyper parameters are observed by conducting a number of experiments. Finally, we have GRU, LSTM networks to boost our model performance with adding those networks to BERT pre-trained model. We do fine-tuning the pre-trained korean-based language model through the methods mentioned above and push the F1 score from baseline up to 89.66. Moreover, some failure attempts give us important lessons and tell us the further direction in a good way.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• 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.

• Speech Sciences
• /
• v.9 no.1
• /
• pp.111-135
• /
• 2002

An annotation model of a non-native speech database has been devised, wherein English is the target language and Korean is the native language. The proposed annotation model features overt transcription of predictable linguistic information in native speech by the dictionary entry and several predefined types of error specification found in native language transfer. The proposed model is, in that sense, different from other previously explored annotation models in the literature, most of which are based on native speech. The validity of the newly proposed model is revealed in its consistent annotation of 1) salient linguistic features of English, 2) contrastive linguistic features of English and Korean, 3) actual errors reported in the literature, and 4) the newly collected data in this study. The annotation method in this model adopts the widely accepted conventions, Speech Assessment Methods Phonetic Alphabet (SAMPA) and the TOnes and Break Indices (ToBI). In the proposed annotation model, SAMPA is exclusively employed for segmental transcription and ToBI for prosodic transcription. The annotation of non-native speech is used to assess speaking ability for English as Foreign Language (EFL) learners.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.59-70
• /
• 2024

We introduce a high-performance named entity recognition (NER) model for written and spoken language. To overcome challenges related to labeled data scarcity and domain shifts, we use transfer learning to leverage our previously developed KorBERT as the base model. We also adopt a meta-pseudo-label method using a teacher/student framework with labeled and unlabeled data. Our model presents two modifications. First, the student model is updated with an average loss from both human- and pseudo-labeled data. Second, the influence of noisy pseudo-labeled data is mitigated by considering feedback scores and updating the teacher model only when below a threshold (0.0005). We achieve the target NER performance in the spoken language domain and improve that in the written language domain by proposing a straightforward rollback method that reverts to the best model based on scarce human-labeled data. Further improvement is achieved by adjusting the label vector weights in the named entity dictionary.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.8
• /
• pp.101-106
• /
• 2017

In this paper, we propose a new teaching-learning model with two-step feedback on programming language learning, which is a basic preliminary learning for programming. Programming learning is aimed at improving problem solving skills and thinking by experiencing problem solving through programming. For programming, the learner must know how to work with the computer and what to do with it. To do this, concrete thinking should be established and described in an accurate programming language. In recent, most studies have focused on the effects of programming learning and have not studied the effects of education on language itself. Therefore, in this study, the teaching-learning model for programming language education is presented and applied to the field, and the results are compared with the existing instructional-teaching model.