• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.278-287
• /
• 2019

Spatial information extraction is to retrieve static and dynamic aspects in natural language text by explicitly marking spatial elements and their relational words. This paper proposes a deep learning approach for spatial information extraction for Korean language using a two-step bidirectional LSTM-CRF ensemble model. The integrated model of spatial element extraction and spatial relation attribute extraction is proposed too. An experiment with the Korean SpaceBank demonstrates the better efficiency of the proposed deep learning model than that of the previous CRF model, also showing that the proposed ensemble model performed better than the single model.

• KIISE Transactions on Computing Practices
• /
• v.22 no.7
• /
• pp.315-319
• /
• 2016

Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.27-35
• /
• 2021

Automatic post editing is a research field that aims to automatically correct errors in machine translation results. This research is mainly being focus on high resource language pairs, such as English-German. Recent APE studies are mainly adopting transfer learning based research, where pre-training language models, or translation models generated through self-supervised learning methodologies are utilized. While translation based APE model shows superior performance in recent researches, as such researches are conducted on the high resource languages, the same perspective cannot be directly applied to the low resource languages. In this work, we apply two transfer learning strategies to Korean-English APE studies and show that transfer learning with translation model can significantly improves APE performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.81-83
• /
• 2022

Understanding research trends is necessary to select research topics and explore related works. Most researchers search representative keywords of interesting domains or technologies to understand research trends. However some conferences in artificial intelligence or data mining fields recently publish hundreds to thousands of papers for each year. It makes difficult for researchers to understand research trend of interesting domains. In our paper, we propose an automatic technology keyphrase extraction method to support researcher to understand research trend for each conference or journal. Keyphrase extraction that extracts important terms or phrases from a text, is a fundamental technology for a natural language processing such as summarization or searching, etc. Previous keyphrase extraction technologies based on pretrained language model extract keyphrases from long texts so performances are degraded in short texts like titles of papers. In this paper, we propose a techonolgy keyphrase extraction model that is robust in short text and considers the importance of the word.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.295-297
• /
• 2007

This study suggests a computational model to inquire the roles of phonological information and orthography information in the process of visual word recognition among the courses of language information processing and the representation types of the mental lexicon. As the result of the study, the computational model showed the phonological and orthographic neighborhood effect among language phenomena which are shown in Korean word recognition, and showed proofs which implies that the mental lexicon is represented as phonological information in the process of Korean word recognition.

• 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.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2021

Spoken language understanding, which aims to understand utterance as naturally as human would, are mostly focused on English language. In this paper, we construct a Korean language dataset for spoken language understanding, which is based on a conversational corpus between reservation system and its user. The domain of conversation is limited to restaurant reservation. There are 7 types of slot tags and 5 types of intent tags in 6857 sentences. When a model proposed in English-based research is trained with our dataset, intent classification accuracy decreased a little, while slot filling F1 score decreased significantly.

• Journal of KIISE:Software and Applications
• /
• v.33 no.1
• /
• pp.17-31
• /
• 2006

Software architecture is the high level model of a software system. It should be specified with ADLs (Architecture Description Languages) for its clarity and preciseness. Most ADLs such as C2SADL have not come into extensive use in industries since ADL users should learn a distinct notation specific to architecture, and ADLs do not address all stakes of the development process that is becoming diversified everyday. On the other hand, UML is a do facto standard general modeling language for software developments. UML provides a consistent notation and various supporting tools during the whole software development cycle. But, UML is a general modeling language and does not provide all concepts that are important to architecture description. UML should be extended in order to precisely model architecture. In this paper, we defined a C2 architecture modeling language as a UML2.0 profile. We applied the defined C2 architecture modeling language to the modeling of a restaurant reservation system.

• Korean Journal of Cognitive Science
• /
• v.3 no.2
• /
• pp.161-174
• /
• 1992

The present discussion is concerned with showing the development of natural language processing and how it is related to information and cognition.On the basis of the computeational model,in which humans are viewed as processors of linguistic structures that use stored knowledge-grammar, lexicon and structures representing the encyclopedic information of the world,such programs of natural language understanding as Winograd's SHRDLU came out.However,such pragmatic factors as contexts and the speaker's beliefs,internts,goals and intentions are not easy to process yet.Language,ingormation and cognition are argued to be closely interrelated,and the study of them,the paper argues,can lead to the development of science on general.