• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.931-934
• /
• 2019

Research using artificial intelligence to generate captions for an image has been studied extensively. However, these systems are unable to create creative stories that include more than one sentence based on image content. A story is a better way that humans use to foster social cooperation and develop social norms. This paper proposes a framework that can generate a relatively short story to describe based on the context of an image. The main contributions of this paper are (1) An unsupervised framework which uses recurrent neural network structure and encoder-decoder model to construct a short story for an image. (2) A huge English novel dataset, including horror and romantic themes that are manually collected and validated. By investigating the short stories, the proposed model proves that it can generate more creative contents compared to existing intelligent systems which can produce only one concise sentence. Therefore, the framework demonstrated in this work will trigger the research of a more robust AI story writer and encourages the application of the proposed model in helping story writer find a new idea.

• Korean Journal of Cognitive Science
• /
• v.14 no.2
• /
• pp.1-13
• /
• 2003

We introduce a way to generate morphologically and syntactically well-formed English sentences when building Korean to English bilingual dictionary for Machine Translation Systems. It has been proved that basic inflectional or structural descriptions for English sentences are by no means enough to generate proper English sentences because of traditional dictionary structures. Furthermore, much research has been focused only on how to disambiguate semantic ambiguities of words in a bilingual dictionary To take advantage of existing paperback Korean to English bilingual dictionary, its automatic conversion to an electronic version and methodologies to assign proper features to the descriptions for well-formed English sentences with minimum human effort have been proposed on the basis of the dictionary-specific structures. This approach was originally motivated for a glossary-based machine translation system, but it can be also applied to large scale dictionary work.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.33-39
• /
• 2020

In the field of Natural Language Processing, Various research such as Translation, POS Tagging, Q&A, and Sentiment Analysis are globally being carried out. Sentiment Analysis shows high classification performance for English single-domain datasets by pretrained sentence embedding models. In this thesis, the classification performance is compared by Korean E-commerce online dataset with various domain attributes and 6 Neural-Net models are built as BOW (Bag Of Word), LSTM[1], Attention, CNN[2], ELMo[3], and BERT(KoBERT)[4]. It has been confirmed that the performance of pretrained sentence embedding models are higher than word embedding models. In addition, practical Neural-Net model composition is proposed after comparing classification performance on dataset with 17 categories. Furthermore, the way of compressing sentence embedding model is mentioned as future work, considering inference time against model capacity on real-time service.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.161-164
• /
• 2006

인터넷이 발전하면서 웹에는 같은 내용을 다양한 언어로 표현한 문서들이 많이 존재한다. 이와 같은 웹 문서의 성질을 이용하여, 이 논문은 웹으로부터 수집된 병렬문서(parallel document)를 이용하여 한영 병렬말뭉치 구축 시스템을 설계하고 구현한다. 이 논문에서 구축과정을 요약하면 다음과 같다. 첫째, 웹 문서수집기를 이용해서 웹으로부터 한영 웹문서(html 문서)를 각각 수집한다. 둘째, 수집된 각 언어의 웹 문서에서 불필요한 내용(태그와 광고 문구 등)을 제거하여 문장을 추출하고, 추출된 문장을 단락단위로 정렬한다. 셋째, 단락단위로 정렬된 문서를 문장정렬(sentence alignment) 방법을 이용해서 문장을 정렬한다. 끝으로 정렬된 병렬문장을 단어 단위로 분리하여 병렬말뭉치를 구축한다. 이와 같은 방법으로 이 논문에서는 약 42만 5천 문장의 한영 병렬말뭉치를 구축하였다.

• Journal of information and communication convergence engineering
• /
• v.20 no.2
• /
• pp.113-124
• /
• 2022

News in the form of web data generates increasingly large amounts of information as unstructured text. The capability of understanding the meaning of news is limited to humans; thus, it causes information overload. This hinders the effective use of embedded knowledge in such texts. Therefore, Automatic Knowledge Extraction (AKE) has now become an integral part of Semantic web and Natural Language Processing (NLP). Although recent literature shows that AKE has progressed, the results are still behind the expectations. This study proposes a method to auto-extract surface knowledge from English news into a machine-interpretable semantic format (triple). The proposed technique was designed using the grammatical structure of the sentence, and 11 original rules were discovered. The initial experiment extracted triples from the Sri Lankan news corpus, of which 83.5% were meaningful. The experiment was extended to the British Broadcasting Corporation (BBC) news dataset to prove its generic nature. This demonstrated a higher meaningful triple extraction rate of 92.6%. These results were validated using the inter-rater agreement method, which guaranteed the high reliability.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.397-400
• /
• 2021

To solve the problem that existing computing methods cannot adequately represent the semantic features of sentences, Siamese TRAT, a semantic feature extraction model based on Transformer encoder is proposed. The transformer model is used to fully extract the semantic information within sentences and carry out deep semantic coding for sentences. In addition, the interactive attention mechanism is introduced to extract the similar features of the association between two sentences, which makes the model better at capturing the important semantic information inside the sentence. As a result, it improves the semantic understanding and generalization ability of the model. The experimental results show that the proposed model can improve the accuracy significantly for the semantic similarity calculation task of English and Chinese, and is more effective than the existing methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.731-732
• /
• 2024

본 논문은 음원 메타데이터 임베딩 방법론을 기반으로 새로운 음원 추천 방법을 제안한다. 사용자 행동 데이터를 활용한 개인 맞춤형 음악 추천 모델은 신규 사용자의 데이터가 부족할 경우, 적절한 추천이 어려운 콜드스타트 현상을 초래할 수 있다. 본 연구에서는 플레이리스트의 음원 메타데이터를 Song sentence 로 구성하고, 고차원 벡터 공간에 임베딩하여 유사도를 계산한 추천 알고리즘을 구축한다. 사용자 행동 데이터가 아닌 음원의 자체적인 정보에 근거하기 때문에 콜드 스타트 현상을 보완하여 사용자에게 편리한 음악 감상 경험을 제공할 수 있을 것으로 기대된다.

• Journal of Internet Computing and Services
• /
• v.1 no.2
• /
• pp.49-59
• /
• 2000

The majority of work done to date on natural language processing has focused on analysis and understanding of language, thus natural language generation had been relatively less attention than understanding, And people even tends to regard natural language generation CIS a simple reverse process of language understanding, However, need for natural language generation is growing rapidly as application systems, especially multi-language machine translation systems on the web, natural language interface systems, natural language query systems need more complex messages to generate, In this paper, we propose an algorithm to generate more flexible and natural sentence using lexical functions of Igor Mel'uk (Mel'uk ＆ Zholkovsky, 1988) and systemic grammar.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.2025-2037
• /
• 1997

The concept-based translation system, which is a part of the Korean spoken language translation system, translates spoken utterances from Korean speech recognizer into one of English, Japanese and Korean in a travel planning task. Our system regulates semantic rather than the syntactic category in order to process the spontaneous speech which tends to be regarded as the one ungrammatical and subject to recognition errors. Utterances are parsed into concept structures, and the generation module produces the sentence of the specified target language. We have developed a token-separator using base-words and an automobile grammar corrector for Korean processing. We have also developed postprocessors for each target language in order to improve the readability of the generation results.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1352-1355
• /
• 1987

This Paper proposed the modified binary n-gram algorithm for the contextual post processing system in English sentence. Backward gram was used to correct the first position error in a word. It is not requires additional storage but more times of comparison it allows interactive correction routine. Experiments were implemented using PASCAL language on a micro computer, IBM PC/XT. This algorithm improves the correction rate around $4{\sim}5%$ on a limited experimental environments.