• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1378-1391
• /
• 2019

In recent years, automatic document summarization has been widely studied in the field of natural language processing thanks to the remarkable developments made using deep learning models. To decode a word, existing models for abstractive summarization usually represent the context of a document using the weighted hidden states of each input word when they decode it. Because the weights change at each decoding step, these weights reflect only the local context of a document. Therefore, it is difficult to generate a summary that reflects the overall context of a document. To solve this problem, we introduce the notion of a general context and propose a model for summarization based on it. The general context reflects overall context of the document that is independent of each decoding step. Experimental results using the CNN/Daily Mail dataset show that the proposed model outperforms existing models.

• The Journal of Korea Robotics Society
• /
• v.4 no.1
• /
• pp.56-61
• /
• 2009

A probability-based data generation is a typical context-generation method that is a not only simple and strong data generation method but also easy to update generation conditions. However, the probability-based context-generation method has been found its natural-born ambiguousness and confliction problems in generated context data. In order to compensate for the disadvantages of the probabilistic random data generation method, a situation propagation network is proposed in this paper. The situation propagating network is designed to update parameters of probability functions are included in probability-based data generation model. The proposed probability-based context-generation model generates two kinds of contexts: one is related to independent contexts, and the other is related to conditional contexts. The results of the proposed model are compared with the results of the probabilitybased model with respect to performance, reduction of ambiguity, and confliction.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.4
• /
• pp.225-232
• /
• 2009

Context-aware technologies for ubiquitous computing are necessary to study the representation of gathered context-information appropriately, the understanding of user's intention using context-information, and the offer of pertinent services for users. In this paper, we propose the WS-CAM(Web Services based Context-Aware Middleware) framework for context-aware computing. WS-CAM provides ample power of expression and inference mechanisms to various context-information using an ontology-based context model. We also consider that WS-CAM is the middleware-independent structure to adopt web services with characteristic of loosely coupling as a matter of communication of context-information. In this paper, we describe a scenario for lecture services based on the ubiquitous computing e e e e e e to verify the utilization of WS-CAM We also show an example of middleware-independent system expansion to display the merits of web-based services. WS-CAM for lecture services represented context-information itodomaits as OWL-based ontology model effectively, and we confirmed the information is inferred to high level context-information by user-defined rules. We also confirmed the context-information is transferred to application services middleware-independently using various web methods provided by web services.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.3-8
• /
• 1999

Previous variable vocabulary speech recognition systems with context-independent acoustic modeling, could not represent the effect of neighboring phonemes. To solve this problem, we use allophone-based context-dependent acoustic model. This paper describes the method to improve acoustic model of the system effectively. Acoustic model is improved by using allophone clustering technique that uses entropy as a similarity measure and the optimal allophone model is generated by changing the number of allophones. We evaluate performance of the improved system by using Phonetically Optimized Words(POW) DB and PC commands(PC) DB. As a result, the allophone model composed of six hundreds allophones improved the recognition rate by 13% from the original context independent model m POW test DB.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2463-2466
• /
• 2003

This paper studied the pattern recognition algorithm and feature parameters for emotion recognition. In this paper, KNN algorithm was used as the pattern matching technique for comparison, and also VQ and GMM were used lot speaker and context independent recognition. The speech parameters used as the feature are pitch, energy, MFCC and their first and second derivatives. Experimental results showed that emotion recognizer using MFCC and their derivatives as a feature showed better performance than that using the Pitch and energy Parameters. For pattern recognition algorithm, GMM based emotion recognizer was superior to KNN and VQ based recognizer

• Journal of Electrical Engineering and information Science
• /
• v.1 no.2
• /
• pp.1-8
• /
• 1996

This paper presents a text-driven discourse analysis system, called DPAS. DPAS constructs a discourse structure by weaving together clauses in the text by finding discourse relations between a clause and the clauses in a context. The basic processing model of DPAS is based on the stack based model of discourse analysis suggested by Grosz and Sidner. We extend the model with dynamic programming method to handle various discourse ambiguities effectively and efficiently. We develop the idea of a context space to keep all information of a context. DPAS parses a text by considering all possible discourse relations between a clause and a context. Since different discourse relations may result in different states of a context, DPAS maintains multiple context spaces for an ambiguous text. Since maintaining all interpretations until the whole text is processed requires too much computing resources, DPAS uses the idea of depth-limited search to limit the search space. If there is more than one discourse relation between an input clause and a context, DPAS constructs context spaces one context space for each discourse relation. Then, DPAS applies heuristics to choose the most desirable context space after it processes some more input clauses. Since the basic idea of DPAS is domain independent, although we used descriptive texts to demonstrate DPAS, we believe the idea of DPAS can be extended to understand other styles of texts.

• Journal of Korean Institute of Industrial Engineers
• /
• v.35 no.1
• /
• pp.51-57
• /
• 2009

There are a variety of users and devices in a context-aware computing environment. In this environment, the service provided to a user may be the composition of diverse services rather than one independent service. Before user's devices provide the composite service to the user, they should perceive user's needs by gathering related information segments from other surrounding devices and/or sensors. We consider a context-aware computing environment providing composite and adapted service to users and propose an information processing model that characterizes the device where the collected data should be processed through services and/or applications. Based on this model, we provide an analytical tool to obtain some performance measures of the context-aware computing environment.

• MALSORI
• /
• v.68
• /
• pp.33-47
• /
• 2008

In this paper, we propose a hybrid acoustic and pronunciation model adaptation method based on context dependency for Korean-English speech recognition. The proposed method is performed as follows. First, in order to derive pronunciation variant rules, an n-best phoneme sequence is obtained by phone recognition. Second, we decompose each rule into a context independent (CI) or a context dependent (CD) one. To this end, it is assumed that a different phoneme structure between Korean and English makes CI pronunciation variabilities while coarticulation effects are related to CD pronunciation variabilities. Finally, we perform an acoustic model adaptation and a pronunciation model adaptation for CI and CD pronunciation variabilities, respectively. It is shown from the Korean-English speech recognition experiments that the average word error rate (WER) is decreased by 36.0% when compared to the baseline that does not include any adaptation. In addition, the proposed method has a lower average WER than either the acoustic model adaptation or the pronunciation model adaptation.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.24-35
• /
• 2022

The purpose of this study was to form a linked model in which local institutions related to lifelong education for the disabled can cooperate based on the Daegu University K-PACE Center. The contents of the study started with recognizing the problem that the adult-centered lifelong education support system does not effectively cope with these factors, even though the independent life of people with developmental disabilities is a major factor determining the quality of life. Regarding this problem recognition, this study primarily emphasized the view that educational support for independent life of people with developmental disabilities should establish the context of the school foundation. The context of the school foundation is established for lifelong education centered on adulthood for people with developmental disabilities because the curriculum is embodied through the standards of subject matter education. In this regard, the Daegu University K-PACE Center, which established a curriculum that supports the independent life of people with developmental disabilities in terms of linking higher and lifelong education, actually reflects the context of the school foundation. As a result, this study prepared a strategy that could be considered as a transition to advance the curriculum organized by the Daegu University K-PACE Center, and the strategy was secondarily reflected as a procedure that could be linked to local lifelong education-related institutions for the disabled. Finally, this study presented a form of transition in which people with developmental disabilities can access the curriculum of lifelong education through the connection of local lifelong education-related institutions for the disabled, centering on the entire life of adulthood.