• ETRI Journal
• /
• v.46 no.1
• /
• pp.35-47
• /
• 2024

This study introduces CR-M-SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding-based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost-effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR-M-SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high-recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1464-1479
• /
• 2018

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the $L_2$ norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.219-224
• /
• 2012

In the communication mobile terminal, Vocabulary recognition system has low recognition rates, because this problems are due to phoneme feature extract from inaccurate vocabulary. Therefore they are not recognize the phoneme and similar phoneme misunderstanding error. To solve this problem, this paper propose the system model, which based on the two step process. First, input phoneme is represent by number which measure the distance of phonemes through phoneme likelihood process. next step is recognize the result through the reliability measure. By this process, we minimize the phoneme misunderstanding error caused by inaccurate vocabulary and perform error correction rate for error provrd vocabulary using phoneme likelihood and reliability. System performance comparison as a result of recognition improve represent 2.7% by method using error pattern learning and semantic pattern.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2008.10a
• /
• pp.90-93
• /
• 2008

In natural language, it is common that repetitive constituents in an expression are to be left out and it is necessary to figure out the constituents omitted at analyzing the meaning of the sentence. This paper is on recognition of boundaries of parallel noun phrases by figuring out constituents omitted. Recognition of parallel noun phrases can greatly reduce complexity at the phase of sentence parsing. Moreover, in natural language information retrieval, recognition of noun with modifiers can play an important role in making indexes. We propose an unsupervised probabilistic model that identifies parallel cores as well as boundaries of parallel noun phrases conjoined by a conjunctive particle. It is based on the idea of swapping constituents, utilizing symmetry (two or more identical constituents are repeated) and reversibility (the order of constituents is changeable) in parallel structure. Semantic features of the modifiers around parallel noun phrase, are also used the probabilistic swapping model. The model is language-independent and in this paper presented on parallel noun phrases in Korean language. Experiment shows that our probabilistic model outperforms symmetry-based model and supervised machine learning based approaches.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.308-310
• /
• 2022

With the rise of the Al wave, task-oriented dialogue systems have become one of the popular research directions in academia and industry. Currently, task-oriented dialogue systems mainly adopt pipelined form, which mainly includes natural language understanding, dialogue state decision making, dialogue state tracking and natural language generation. However, pipelining is prone to error propagation, so many task-oriented dialogue systems in the market are only for single-round dialogues. Usually single- domain dialogues have relatively accurate semantic understanding, while they tend to perform poorly on multi-domain, multi-round dialogue datasets. To solve these issues, we developed a paddle-based multi-domain task-oriented Chinese dialogue system. It is based on NEZHA-base pre-training model and CrossWOZ dataset, and uses intention recognition module, dichotomous slot recognition module and NER recognition module to do DST and generate replies based on rules. Experiments show that the dialogue system not only makes good use of the context, but also effectively addresses long-term dependencies. In our approach, the DST of dialogue tracking state is improved, and our DST can identify multiple slotted key-value pairs involved in the discourse, which eliminates the need for manual tagging and thus greatly saves manpower.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.47-55
• /
• 2024

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.5 s.112
• /
• pp.1-14
• /
• 2005

This study describes the recognition and the application of materials corresponding to the formative language of landscape design as the formative process of creating connote forms and meanings in a space. The purpose of this study is to propose the significance of materiality not only for conveying the meaning of landscape but also for providing expanded experience through synesthetic perception. The study consists of two parts: (1) The concept of materiality in landscape architecture is studied in three categories, which are divided in chronological order when the recognition of materials was changed. (2) Based on this exploration of the concept of materiality and the ways of expressing it that have developed from landscape arts to landscape architecture, the significance of materiality as the medium of contemporary landscape design is proposed. Breaking from previous technical and engineering approaches to materials and from a vision-centered recognition of materials, this study focuses on aesthetic and semantic aspects of materiality and is based on multidimensional recognition though synesthesia. Materiality has significance not only as the dynamic medium that carries the meaning of landscape by providing connections with the surrounding environmental context, but also as the engagement medium that expands observers' experiences with the environment through synesthesia. The study of materiality as the medium of landscape design would contribute to expanding the scope of the language of landscape design and to expressing the meaning of landscape through materiality being revealed on the basis of converted recognition of materials.

• Journal of dental hygiene science
• /
• v.20 no.3
• /
• pp.163-170
• /
• 2020

Background: Job satisfaction of dental hygienists has been discussed continuously in dental hygiene research. It has been the most representative performance variable in dental and human resource management. However, in quantitative research, most of the studies have analyzed the causal relationship with variables related to dental hygienists' job satisfaction. The existing qualitative research contains only the studies that targeted dental hygienists with an experience of more than 10 years. The present study aimed to understand and to characterize the job satisfaction of dental hygienists with an experience of 2 to 10 years and to compare it with the qualitative research on dental hygienists with an experience of 10 or more years. Methods: An in-depth interview of dental hygienists with 2 to 10 years of experience working in 10 dental clinics was conducted. For data analysis, Giorgi's analysis method was used. Results: After analyzing the meaning of job satisfaction of dental hygienists, 180 semantic words and 19 subcategories were derived. The results of the interview were categorized into for central meanings: recognition and rewards, work experience and ability improvement, occupational characteristics, and work characteristics. Recognition and rewards included workplace recognition, patient recognition, self-effort and recognition, and the feeling of being rewarded. Work experience and ability improvement included various work experiences and factors relates to improving the work ability. Occupational characteristics included professional job, interest and persistence, job extensibility, and no burden of employment. Work characteristics included working conditions and separation of work and private life. Conclusion: The development of tools to measure the level of dental hygienists' job satisfaction after long-term service and to conduct follow-up research regarding ways and effects to improve job satisfaction is needed.

• Journal of the Korean housing association
• /
• v.19 no.3
• /
• pp.105-115
• /
• 2008

This study examines and analyzes a variety of apartment roof style for 147 apartment complexes built in the Gwangju metropolitan city in order to determine the style that is most preferred. The results of this study are as follows. Most of apartment houses built in the Gwangju metropolitan city are 11 to 15 stories followed by apartments that have less than 5 stories, with fewer apartments that have 16 to 20 stories. According to roof styles, the eyebrow roof A type is the most common, followed by the plane roof A type, the sloped roof B type and the sloped roof C type, while 2/3 of all roof types have either an eyebrow roof A type or a plane roof A type. Using images of these roof types to determine those that are preferred, the decorative roof C type is most preferred, followed by the sloped roof B and C types. According to recognition of adjective pairs, decorative roof C type showed a higher recognition for the categories of unique, decorative, three dimensional and novel, the sloped roof B type showed a higher recognition for the categories of three dimensional, decorative and structured while the sloped roof C type showed a higher recognition in the decorative, novel, varied and three dimensional categories. In the correlations between image preference and recognition scale of roof styles of apartment houses, decorative roof C type showed a significant correlation between adjective pairs with the calm image, the sloped roof B type with the intimate image, while the sloped roof C type showed a correlation between static and ordered with the easy image. Therefore, for the design of future apartment roofs, decorative roof C type requires more consideration of visual aspects that are related to a sense of unity, while further morphological factors needs to be adopted with sloped roof B and C types.

• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.31-39
• /
• 2016

In emergency dispatching at 119 Command & Dispatch Center, some inconsistencies between the 'standard emergency aid system' and 'dispatch protocol,' which are both mandatory to follow, cause inefficiency in the dispatcher's performance. If an emergency dispatch system uses automatic speech recognition (ASR) to process the dispatcher's protocol speech during the case registration, it instantly extracts and provides the required information specified in the 'standard emergency aid system,' making the rescue command more efficient. For this purpose, we have developed a Korean large vocabulary continuous speech recognition system for 400,000 words to be used for the emergency dispatch system. The 400,000 words include vocabulary from news, SNS, blogs and emergency rescue domains. Acoustic model is constructed by using 1,300 hours of telephone call (8 kHz) speech, whereas language model is constructed by using 13 GB text corpus. From the transcribed corpus of 6,600 real telephone calls, call logs with emergency rescue command class and identified major symptom are extracted in connection with the rescue activity log and National Emergency Department Information System (NEDIS). ASR is applied to emergency dispatcher's repetition utterances about the patient information. Based on the Levenshtein distance between the ASR result and the template information, the emergency patient information is extracted. Experimental results show that 9.15% Word Error Rate of the speech recognition performance and 95.8% of emergency response detection performance are obtained for the emergency dispatch system.