• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.227-232
• /
• 2020

본 논문은 의미역 주석(Semantic Role Labeling) 자원인 FrameNet을 준구어 말뭉치인 드라마 대본에 주석하는 과정과 주석 결과에 대해 서술한다. 본 논문에서는 프레임 - 프레임 논항 구조의 주석 범위를 한 문장에서 여러 발화로 이루어진 장면 (Scene) 단위의 대본으로 확장하여 문장 내에서 생략된 프레임 논항(Null-Instantiated Frame Elements)을 장면 단위 대본 내의 다른 발화에서 복원하였다. 본 논문은 프레임 자동 분석기를 통해 동일한 드라마의 한국어, 영어 대본에 FrameNet 주석을 한 드라마 대본을 선발된 주석자에 의해 대상 어휘 적합성 평가, 프레임 적합성 평가, 생략된 프레임 논항 복원을 실시하고, 자동 주석된 대본과 주석자 작업 후의 대본 결과를 비교한 결과와 예시를 제시한다. 주석자가 자동 주석된 대본 중 총 2,641개 주석 (한국어 1,200개, 영어 1,461개)에 대하여 대상 어휘 적합성 평가를 실시하여 한국어 190개 (15.83%), 영어 226개 (15.47%)의 부적합 대상 어휘를 삭제하였다. 프레임 적합성 평가에서는 대상 어휘에 자동 주석된 프레임의 적합성을 평가하여 한국어 622개 (61.68%), 영어 473개 (38.22%)의 어휘에 대하여 새로운 프레임을 부여하였다. 생략된 프레임 논항을 복원한 결과 작업된 평균 프레임 논항 개수가 한국어 0.780개에서 2.519개, 영어 1.290개에서 2.253개로 증가하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.4
• /
• pp.1-7
• /
• 2004

In this thesis, we introduce a parsing method which use information of the post position in Korean to get the exact parsing tree. In order to implement this method we classified categories of the predicates, and defined sentence-types based on these categories. We tried to make parsing using the method grasping the grammatical role of the noun phrase that have to exist in each sentence-type. In parser control mechanism, we use some heuristics based on linguistic frame. We use conditional unification to implement analysis. It is Possible to reduce ambiguous because the parsing method suggested helps to Prune the branches which are unnecessary.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.109-112
• /
• 2001

This paper proposes an efficient algorithm of extracting anchor blocks for a semantic structure of a news video. We define the FRFD to calculate the frame difference of anchor face position rather than simply uses the general frame difference. Since, The FRFD value is sensitive to existing face in frame, anchor block can be efficiently extracted. In this paper, an algorithm to extract a face position using partial decoded MPEG data is also proposed. In this way a news video can be structured semantically using the extracted anchor blocks.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2E
• /
• pp.14-23
• /
• 1996

This paper is a on the neural network to recognize the phonemes, the weight initialization to reduce learning speed, and LR parser for continuous speech recognition. The neural network spots the phonemes in continuous speech and LR parser parses the output of neural network. The whole phonemes recognized in neural network are divided into several groups which are grouped by the similarity of phonemes, and then each group consists of neural network. Each group of neural network to recognize the phonemes consisits of that recognize the phonemes of their own group and VGNN(Verify Group Neural Network) which judges whether the inputs are their own group or not. The weights of neural network are not initialized with random values but initialized from learning data to reduce learning speed. The LR parsing method applied to this paper is not a method which traces a unique path, but one which traces several possible paths because the output of neural network is not accurate. The parser processes the continuous speech frame by frame as accumulating the output of neural network through several possible paths. If this accumulated path-value drops below the threshold value, this path is deleted in possible parsing paths. This paper applies the continuous speech recognition system to the threshold value, this path is deleted in possible parsing paths. This paper applies the continuous speech recognition system to the continuous Korea digits recognition. The recognition rate of isolated digits is 97% in speaker dependent, and 75% in speaker dependent. The recognition rate of continuous digits is 74% in spaker dependent.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.119-123
• /
• 2020

이벤트 추출은 텍스트에서 구조화된 이벤트를 분석하는 것이다. 본 논문은 대화문에서 발생하는 다양한 종류의 이벤트를 다루기 위해 이벤트 스키마를 프레임넷으로 정한다. 대화문에서의 이벤트 논항은 이벤트가 발생하는 문장 뿐만 아니라 다른 문장 또는 대화에 참여하는 발화자에서 발생할 수 있다. 대화문 주석 데이터의 부재로 대화문에서의 프레임 파싱 연구는 진행되지 않았다. 본 논문이 제안하는 모델은 대화문에서의 이벤트 논항 구간이 주어졌을 때, 논항 구간의 역할을 식별하는 모델이다. 해당 모델은 이벤트를 유발한 어휘, 논항 구간, 논항 역할 간의 관계를 학습한다. 대화문 주석 데이터의 부족을 극복하기 위해 문어체 주석 데이터인 한국어 프레임넷을 활용하여 전이학습을 진행한다. 이를 통해 정확도 51.21%를 달성한다.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.47-60
• /
• 2012

Video data comes in the form of the unstructured and the complex structure. As the importance of efficient management and retrieval for video data increases, studies on the video parsing based on the visual features contained in the video contents are researched to reconstruct video data as the meaningful structure. The early studies on video parsing are focused on splitting video data into shots, but detecting the shot boundary defined with the physical boundary does not cosider the semantic association of video data. Recently, studies on structuralizing video shots having the semantic association to the video scene defined with the semantic boundary by utilizing clustering methods are actively progressed. Previous studies on detecting the video scene try to detect video scenes by utilizing clustering algorithms based on the similarity measure between video shots mainly depended on color features. However, the correct identification of a video shot or scene and the detection of the gradual transitions such as dissolve, fade and wipe are difficult because color features of video data contain a noise and are abruptly changed due to the intervention of an unexpected object. In this paper, to solve these problems, we propose the Scene Detector by using Color histogram, corner Edge and Object color histogram (SDCEO) that clusters similar shots organizing same event based on visual features including the color histogram, the corner edge and the object color histogram to detect video scenes. The SDCEO is worthy of notice in a sense that it uses the edge feature with the color feature, and as a result, it effectively detects the gradual transitions as well as the abrupt transitions. The SDCEO consists of the Shot Bound Identifier and the Video Scene Detector. The Shot Bound Identifier is comprised of the Color Histogram Analysis step and the Corner Edge Analysis step. In the Color Histogram Analysis step, SDCEO uses the color histogram feature to organizing shot boundaries. The color histogram, recording the percentage of each quantized color among all pixels in a frame, are chosen for their good performance, as also reported in other work of content-based image and video analysis. To organize shot boundaries, SDCEO joins associated sequential frames into shot boundaries by measuring the similarity of the color histogram between frames. In the Corner Edge Analysis step, SDCEO identifies the final shot boundaries by using the corner edge feature. SDCEO detect associated shot boundaries comparing the corner edge feature between the last frame of previous shot boundary and the first frame of next shot boundary. In the Key-frame Extraction step, SDCEO compares each frame with all frames and measures the similarity by using histogram euclidean distance, and then select the frame the most similar with all frames contained in same shot boundary as the key-frame. Video Scene Detector clusters associated shots organizing same event by utilizing the hierarchical agglomerative clustering method based on the visual features including the color histogram and the object color histogram. After detecting video scenes, SDCEO organizes final video scene by repetitive clustering until the simiarity distance between shot boundaries less than the threshold h. In this paper, we construct the prototype of SDCEO and experiments are carried out with the baseline data that are manually constructed, and the experimental results that the precision of shot boundary detection is 93.3% and the precision of video scene detection is 83.3% are satisfactory.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.10A
• /
• pp.886-895
• /
• 2005

As the networked media technology have been grown in recent, there have been many research works to deliver high-quality video such as HDV and HDTV over the Internet. To realize high-quality media service over the Internet, however, the network adaptive streaming scheme is required to adopt to the dynamic fluctuation of underlying networks. In this paper, we design and implement the network-adaptive HD(high definition) MPEG-2 streaming system employing the frame-based prioritized packetization. Delivered video is inputted from the JVC HDV camera to the streaming sewer in real-time. It has a bit-rate of 19.2 Mbps and is multiplexed to the MPEG-2 TS (MPEG-2 MP@HL). For the monitoring of network status, the packet loss rate and the average jitter are measured by using parsing of RTP packet header in the streaming client and they are sent to the streaming server periodically The network adaptation manager in the streaming server estimates the current network status from feedback packets and adaptively adjusts the sending rate by frame dropping. For this, we propose the real-time parsing and the frame-based prioritized packetization of the TS packet. The proposed system is implemented in software and evaluated over the LAN testbed. The experimental results show that the proposed system can enhance the end-to-end QoS of HD video streaming over the best-effort network.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.4A
• /
• pp.421-430
• /
• 2006

In this paper, we propose a practical implementation of network-adaptive HD(high definition) MPEG-2 video streaming with a cross-layered channel monitoring(CLM) over the IEEE 802.11a WLAN(wireless local area network). For wireless channel monitoring, AP(access point) periodically measures the MAC(medium access control) layer transmission information and sends the monitoring information to a streaming server. This makes that the streaming server reacts more quickly as well as efficiently to the fluctuated wireless channel than that of the end-to-end monitoring(E2EM) scheme for the video adaptation. The streaming sewer dynamically performs the priority-based frame dropping to adjust the video sending rate according to the measured wireless channel condition. For this purpose, our streaming system nicely provides frame-based prioritized packetization by using a real-time stream parsing module. Various evaluation results over an IEEE 802.11a WLAM testbed are provided to verify the intended QoS adaptation capability The experimental results show that the proposed system can effectively mitigate the quality degradation of video streaming caused by the fluctuations of time-varying wireless channel condition.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.3
• /
• pp.78-87
• /
• 2002

A macroblock(MB) in MPEG coded domain can have zero, one, or two motion vectors depending on its frame type and prediction direction (forward-, backward-, or hi-directionally). In this paper, we propose a method that converts these motion vectors on MPEG coded domain as a uniform set, independent of the frame type and the direction of prediction, and directly utilizes these re-analyzed motion vectors for understanding video contents. Also, using this frame-type-independent motion vector, we propose novel methods for detecting and tracking moving objects with frame-based detection accuracy on the compressed domain. These algorithms are performed directly from the MPEG bitstreams after VLC decoding with little time consumption. Experimental results show validity and outstanding performance of our methods.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.122-127
• /
• 2016

본 논문에서서는 질의응답 시스템을 위한 자연언어 질의 이해를 위하여 프레임 시멘틱스 기반 의미 분석방식을 제안한다. 지식베이스에 의존적인 질의 이해는 지식베이스의 불완전성에 의해 충분한 정보를 분석하지 못한다는 점에 착안하여, 질의의 술부-논항구조 및 그 의미에 대한 분석을 수행하여 자연언어 질의에서 나타난 정보들을 충분히 파악하고자 하였다. 본 시스템은 자연언어 질의를 입력으로 받아 이를 프레임 시멘틱스의 구조에 기반하여 기계가 읽을 수 있는 임의의 RDF 표현방식의 모형 쿼리를 생성한다.