Learn More
Existing works indicate that the absence of explicit discourse connectives makes it difficult to recognize implicit discourse relations. In this paper we attempt to overcome this difficulty for implicit relation recognition by automatically inserting discourse connectives between arguments with the use of a language model. Then we propose two algorithms to(More)
Answer ranking is very important for cQA services due to the high variance in the quality of answers. Most existing works in this area focus on using various features or employing machine learning techniques to address this problem. Only a few of them noticed and involved user profile information in this particular task. In this work, we assume the close(More)
This paper describes our approach to the automatic identification of semantic relations between nominals in English sentences. The basic idea of our strategy is to develop machine-learning classifiers which: (1) make use of class-independent features and classifier; (2) make use of a simple and effective feature set without high computational cost; (3) make(More)
Implicit discourse relation recognition is difficult due to the absence of explicit discourse connectives between arbitrary spans of text. In this paper, we use language models to predict the discourse con-nectives between the arguments pair. We present two methods to apply the predicted connectives to implicit discourse relation recognition. One is to use(More)
Landmine detection is an available application of Synthetic Aperture Radar (SAR). According to the double-hump structure of a landmine in SAR images, a new approach is proposed for landmine discrimination with sparse representation. First, the total variation (TV) algorithm is used to denoise. Second, a sub-dictionary is obtained within the narrow limits of(More)
—In order to gain consistent focusing quality all over the imaging region for wide-beam wide-swath airborne synthetic aperture radar (SAR), higher motion compensation (MoCo) accuracy at the edge of the swath is needed. In this letter, an improved MoCo approach is proposed, and its performance is validated by using simulated data, as well as real data(More)
To generalize the image domain GMTI methods for slow moving targets to be suitable for detection fast moving targets with multi-channel ultra-wide band (UWB) SAR system, the representation of moving targets in multi-channel UWB SAR images is studied in this paper. By analyzing the local back projection (LBP) SAR imaging process for the moving target, this(More)
For the vehicle-mounted forward-looking synthetic aperture radar (SAR), detecting algorithms should be effective, robust and real-time. This paper proposed a fast statistic detecting algorithm based on circulatory iteration. We also presented feasible methods to select the optimal parameters of constant false alarm rate (CFAR) detector. Experiment results(More)
  • 1