• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1452-1463
• /
• 2004

The requirement of automatic video summary is increasing as bi-directional broadcasting contents and various user requests and preferences for the bi -directional broadcast environment are increasing. Automatic video summary is needed for an efficient management and usage of many contents in service provider as well. In this paper, we propose a method to generate a content-based summary of linguistic educational videos automatically. First, shot-boundaries and keyframes are generated from linguistic educational video and then multiple(low-level) visual features are extracted. Next, the semantic parts (Explanation part, Dialog part, Text-based part) of the linguistic educational video are generated using extracted visual features. Lastly the XMI- document describing summary information is made based on HieraTchical Summary architecture oi MPEG-7 MDS (Multimedia I)escription Scheme). Experimental results show that our proposed algorithm provides reasonable performance for automatic summary of linguistic educational videos. We verified that the proposed method is useful ior video summary system to provide various services as well as management of educational contents.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.341-354
• /
• 2023

The title of a document is the brief summarization of the document. Readers can easily understand a document if we provide them with its title in their preferred styles and the languages. In this research, we propose a cross-lingual and style-based title generation model using multiple adapters. To train the model, we need a parallel corpus in several languages with different styles. It is quite difficult to construct this kind of parallel corpus; however, a monolingual title generation corpus of the same style can be built easily. Therefore, we apply a zero-shot strategy to generate a title in a different language and with a different style for an input document. A baseline model is Transformer consisting of an encoder and a decoder, pre-trained by several languages. The model is then equipped with multiple adapters for translation, languages, and styles. After the model learns a translation task from parallel corpus, it learns a title generation task from monolingual title generation corpus. When training the model with a task, we only activate an adapter that corresponds to the task. When generating a cross-lingual and style-based title, we only activate adapters that correspond to a target language and a target style. An experimental result shows that our proposed model is only as good as a pipeline model that first translates into a target language and then generates a title. There have been significant changes in natural language generation due to the emergence of large-scale language models. However, research to improve the performance of natural language generation using limited resources and limited data needs to continue. In this regard, this study seeks to explore the significance of such research.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.576-581
• /
• 2021

패러프레이즈란 어떤 문장을 같은 의미를 가지는 다른 단어들을 사용하여 표현한 것들을 의미한다. 이는 정보 검색, 다중 문서 요약, 질의응답 등 여러 자연어 처리 분야에서 중요한 역할을 한다. 특히, 양질의 패러프레이즈 코퍼스를 얻는 것은 많은 시간 및 비용이 소요된다. 이러한 문제점을 해소하기 위해 본 논문에서는 문장 유사도를 이용한 패러프레이즈 쌍을 구축하고, 또 구축한 패러프레이즈 쌍을 이용하여 기계 학습을 통해 새로운 패러프레이즈을 생성한다. 제안 방식으로 생성된 패러프레이즈 쌍은 기존의 구축되어 있는 코퍼스 내 나타나는 표현들로만 구성된 페러프레이즈 쌍이라는 단점이 존재한다. 이러한 단점을 해소하기 위해 기계 학습을 이용한 실험을 진행하여 새로운 표현에 대한 후보군을 추출하는 방법을 적용하여 새로운 표현이라고 볼 수 있는 후보군들을 추출하여 기존의 코퍼스 내 새로운 표현들이 생성된 것을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.141-150
• /
• 2008

In this mobile computing environment, data broadcasting is widely used to resolve the problem of limited power and bandwidth of mobile equipments. Most previous broadcast indexing methods concentrate on flat data. However. with the growing popularity of XML, an increasing amount of information is being stored and exchanged in the XML format. We propose a novel indexing method. called TOP tree(Tree Ordering based Path summary tree), for indexing XML document on mobile broadcast environments. TOP tree is a path summary tree which provides a concise structure summary at group level using global IDs and element information at local level using local IDs. Based on the TOP tree representation, we suggest a broadcast stream generation and query Processing method that efficiently handles not only simple Path queries but also multiple path queries. We have compared our indexing method with other indexing methods. Evaluation results show that our approaches can effectively improve the access time and tune-in time in a wireless broadcasting environment.