Search is a central component of any statistical machine translation system. We describe the search for phrase-based SMT in detail and show its importance for achieving good translation quality. We introduce an explic...
详细信息
This paper presents a MapReduce algorithm for computing pairwise document similarity in large document collections. MapReduce is an attractive framework because it allows us to decompose the inner products involved in...
详细信息
We present a method to classify images into different categories of pornographic content to create a system for filtering pornographic images from network traffic. Although different systems for this application were ...
详细信息
ISBN:
(纸本)9781424421749
We present a method to classify images into different categories of pornographic content to create a system for filtering pornographic images from network traffic. Although different systems for this application were presented in the past, most of these systems are based on simple skin colour features and have rather poor performance. Recent advances in the image recognition field in particular for the classification of objects have shown that bag-of-visual-words-approaches are a good method for many image classification problems. The system we present here, is based on this approach, uses a task-specific visual vocabulary and is trained and evaluated on an image database of 8500 images from different categories. It is shown that it clearly outperforms earlier systems on this dataset and further evaluation on two novel web-traffic collections shows the good performance of the proposed system.
This paper presents an experimental study of environment recognition and movement control of an autonomous two-wheeled mobile robot using infrared range finding sensors. PSD sensors are arranged to detect obstacles an...
详细信息
This paper presents an experimental study of environment recognition and movement control of an autonomous two-wheeled mobile robot using infrared range finding sensors. PSD sensors are arranged to detect obstacles and walls in the surroundings of the robot, and environment features are estimated using a set of range sensors data. The experimental mobile robot uses incremental encoders mounted on the wheels to locate itself in a small area. Using these sensors, some intelligent behaviors, such as wall following and obstacle rounding, have been implemented. Upon these behavior modules, the behavior control system is constructed for sensory navigation without any environment map and global selflocalization. The experimental results show that the mobile robot can carry out a navigation task, even when the robot knows little about the environment.
This paper presents an experimental study of distributed cooperative formation control of a team of autonomous mobile robots. Formation control demands that a team of robots keep a specified pattern while moving in a ...
详细信息
This paper presents an experimental study of distributed cooperative formation control of a team of autonomous mobile robots. Formation control demands that a team of robots keep a specified pattern while moving in a cluttered environment. So reactive control behaviors for keeping formation and obstacle avoidance are described. The behavioral decision to direct the movement of robot is made by the arbitration of primitive behaviors. For a team of two robots, control experiments were conducted using small mobile robots with infrared photo transistors and LEDs mounted on the front and back of the robot body, respectively. Simulations and real experiments using two mobile robots were successfully performed.
We present a characterization of a useful class of skills based on a graphical representation of an agent's interaction with its environment. Our characterization uses betweenness, a measure of centrality on graph...
ISBN:
(纸本)9781605609492
We present a characterization of a useful class of skills based on a graphical representation of an agent's interaction with its environment. Our characterization uses betweenness, a measure of centrality on graphs. It captures and generalizes (at least intuitively) the bottleneck concept, which has inspired many of the existing skill-discovery algorithms. Our characterization may be used directly to form a set of skills suitable for a given task. More importantly, it serves as a useful guide for developing incremental skill-discovery algorithms that do not rely on knowing or representing the interaction graph in its entirety.
Significant progress can be made in the part of elementary school education that relies on intelligent tutoring systems (ITS), if the role of a referee and a peer advisor will be performed by a pedagogical agent that ...
详细信息
Implementation of agency in a cognitive system implies that certain beliefs, values and/or goals represented in the system become, if implicitly, attributed to the self of the agent. When the cognitive system becomes ...
详细信息
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. We show that adaptation approaches with ...
详细信息
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. We show that adaptation approaches with a limited number of free parameters such as linear transform-based approaches are robust in the face of frame labeling errors whereas adaptation approaches with a large number of free parameters such as MAP are sensitive to the quality of the supervision and hence benefit most from use of confidences. Different approaches for using confidence information in adaptation are investigated. This analysis shows that a thresholding approach is effective in that it improves the frame labeling accuracy with little detrimental effect on frame recall. Experimental results show an absolute WER reduction of 2.1% over a CMLLR adapted system on a video transcription task.
This paper proposes a method to calculate the confidence score for out-of-vocabulary (OOV) word verification based on the Output Probability Distribution (OPD) of phoneme HMMs. Compared with input vector for dynamic g...
详细信息
This paper proposes a method to calculate the confidence score for out-of-vocabulary (OOV) word verification based on the Output Probability Distribution (OPD) of phoneme HMMs. Compared with input vector for dynamic garbage model, OPD vector contains more information than the sorted probabilities. Confidence score of each phoneme is calculated by SVM with OPD vectors as input. Hypotheses are accepted or rejected based on this confidence score. Experimental results showed that the proposed method achieved lower EER in word verification task than the conventional dynamic garbage model.
暂无评论