• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.121-128
• /
• 2018

A Korean morphological analyzer adopts sequence-to-sequence (seq2seq) model, which can generate an output sequence of different length from an input. In general, a seq2seq based Korean morphological analyzer takes a syllable-unit based sequence as an input, and output a syllable-unit based sequence. Syllable-based morphological analysis has the advantage that unknown words can be easily handled, but has the disadvantages that morpheme-based information is ignored. In this paper, we propose a reranking model as a post-processor of seq2seq model that can improve the accuracy of morphological analysis. The seq2seq based morphological analyzer can generate K results by using a beam-search method. The reranking model exploits morpheme-unit embedding information as well as n-gram of morphemes in order to reorder K results. The experimental results show that the reranking model can improve 1.17% F1 score comparing with the original seq2seq model.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.627-629
• /
• 2018

영단어를 음역 하는 방법으로 규칙 기반 방법, 통계 기반 방법, 최대 엔트로피 기반 방법 등이 연구되어 왔다. 본 연구에서는 최근 기계 번역에서 우수한 성능을 보인 Sequence-to-Sequence 모델을 영어-한글 음차 표기에 적용해보았다. 실험결과, 다른 방법에 비해 우수한 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.517-519
• /
• 2022

In 5G network environment, proactive mobility management is essential as 5G mobile networks provide new services with ultra-low latency through dense deployment of small cells. The importance of a system that actively controls device handover is emerging and it is essential to predict mobile trajectory during handover. Sequence-to-sequence model is a kind of deep learning model where it converts sequences from one domain to sequences in another domain, and mainly used in natural language processing. In this paper, we developed a system for predicting mobile trajectory in a wireless network environment using sequence-to-sequence model. Handover speed can be increased by utilize our sequence-to-sequence model in actual mobile network environment.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.5
• /
• pp.267-278
• /
• 2017

As the same letter can be pronounced differently depending on word contexts, one should refer to a lexicon in order to pronounce a word correctly. Phonetic alphabets that lexicons adopt as well as pronunciations that lexicons describe for the same word can be different from lexicon to lexicon. In this paper, we use a sequence-to-sequence model that is widely used in deep learning research area in order to convert automatically from one pronunciation to another. The 12 seq2seq models are implemented based on pronunciation training data collected from 4 different lexicons. The exact accuracy of the models ranges from 74.5% to 89.6%. The aim of this study is the following two things. One is to comprehend a property of phonetic alphabets and pronunciations used in various lexicons. The other is to understand characteristics of seq2seq models by analyzing an error.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.17-23
• /
• 2018

We proposed a LSTM-based RNN model that can effectively perform the automatic spacing characteristics. For those long or noisy sentences which are known to be difficult to handle within Neural Network Learning, we defined a proper input data format and decoding data format, and added dropout, bidirectional multi-layer LSTM, layer normalization, and attention mechanism to improve the performance. Despite of the fact that Sejong corpus contains some spacing errors, a noise-robust learning model developed in this study with no overfitting through a dropout method helped training and returned meaningful results of Korean word spacing and its patterns. The experimental results showed that the performance of LSTM sequence-to-sequence model is 0.94 in F1-measure, which is better than the rule-based deep-learning method of GRU-CRF.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.101-107
• /
• 2020

For Korean language processing, morphological analysis is a critical component that requires extensive work. This morphological analysis can be conducted in an end-to-end manner without requiring a complicated feature design using a sequence-to-sequence model. However, the sequence-to-sequence model has a time complexity of O(n²) for an input length n when using the attention mechanism technique for high performance. In this study, we propose a linear-time Korean morphological analysis model using a local monotonic attention mechanism relying on monotonic alignment, which is a characteristic of Korean morphological analysis. The proposed model indicates an extreme improvement in a single threaded environment and a high morphometric F1-measure even for a hard attention model with the elimination of the attention mechanism formula.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1392-1398
• /
• 2008

This paper presents a Petri Net (PN) based disassembly sequence planning model with precedence operations. All feasible disassembly sequences are generated by a disassembly tree and a disassembly sequence is determined using the disassembly precedence and disassembly value matrix, The precedence of disassembly operations is determined through a disassembly tree and the value of disassembly is induced by economic analysis in the end-of-life phase. To solve the disassembly sequence planning model with precedence operations, a heuristic algorithm based on PNs is developed. The developed algorithm generates and searches a partial reachability graph to arrive at an optimal or near-optimal disassembly sequence based on the firing sequence of transitions of the PN model. A refrigerator is shown as an example to demonstrate the effectiveness of proposed model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.2-4
• /
• 2023

Sequence data plays an important role in the field of intelligence, especially for industrial control, traffic control and other aspects. Finding abnormal parts in sequence data has long been an application field of AI technology. In this paper, we propose an anomaly detection method for sequence data using a diffusion model. The diffusion model has two major advantages: interpretability derived from rigorous mathematical derivation and unrestricted selection of backbone models. This method uses the diffusion model to predict and reconstruct the sequence data, and then detects the abnormal part by comparing with the real data. This paper successfully verifies the feasibility of the diffusion model in the field of anomaly detection. We use the combination of MLP and diffusion model to generate data and compare the generated data with real data to detect anomalous points.

• Journal of Korea Water Resources Association
• /
• v.54 no.3
• /
• pp.157-166
• /
• 2021

Forecasting dam inflow based on high reliability is required for efficient dam operation. In this study, deep learning technique, which is one of the data-driven methods and has been used in many fields of research, was manipulated to predict the dam inflow. The Long Short-Term Memory deep learning with Sequence-to-Sequence model (LSTM-s2s), which provides high performance in predicting time-series data, was applied for forecasting inflow of Soyang River dam. Various statistical metrics or evaluation indicators, including correlation coefficient (CC), Nash-Sutcliffe efficiency coefficient (NSE), percent bias (PBIAS), and error in peak value (PE), were used to evaluate the predictive performance of the model. The result of this study presented that the LSTM-s2s model showed high accuracy in the prediction of dam inflow and also provided good performance for runoff event based runoff prediction. It was found that the deep learning based approach could be used for efficient dam operation for water resource management during wet and dry seasons.