This paper proposes an integrated method for extracting the time information of events from Japanese news archives. We first utilize a new pattern-based method named TRE/ERT combined with a neural-based model to extract all temporal expressions possibly related with an event. Then, we apply a simple but efficient clustering and narrowing process to summarize these temporal expressions into a small time frame for events lasting shorter than a day, or time frames for the beginning and the end days of the events for events spanning multiple days. We conducted two experiments where the results show that when working with one-day events, our system has a precision high up to 57% and the rate that the actual date of the event falls in our extracted time frame reaches 100% as long as the event name is found in the archive. The results also show that our system works with multiple-day events, but needs further improvements to get better results.

The differentiable implementation of logic yields a seamless combination of symbolic reasoning and deep neural networks. Recent research, which has developed a differentiable framework to learn logic programs from examples, can even acquire reasonable solutions from noisy datasets. However, this framework severely limits expressions for solutions, e.g., no function symbols are allowed, and the shapes of clauses are fixed. As a result, the framework cannot deal with structured examples. Therefore we propose a new framework to learn logic programs from noisy and structured examples, including the following contributions. First, we propose an adaptive clause search method by looking through structured space, which is defined by the generality of the clauses, to yield an efficient search space for differentiable solvers. Second, we propose for ground atoms an enumeration algorithm, which determines a necessary and sufficient set of ground atoms to perform differentiable inference functions. Finally, we propose a new method to compose logic programs softly, enabling the system to deal with complex programs consisting of several clauses. Our experiments show that our new framework can learn logic programs from noisy and structured examples, such as sequences or trees. Our framework can be scaled to deal with complex programs that consist of several clauses with function symbols.

Computing the similarity between two data points plays a vital role in many machine learning algorithms. Metric learning has the aim of learning a good metric automatically from data. Most existing studies on metric learning for tree-structured data have adopted the approach of learning the tree edit distance. However, the edit distance is not amenable for big data analysis because it incurs high computation cost. In this paper, we propose a new metric learning approach for tree-structured data with pq-grams. The pq-gram distance is a distance for ordered labeled trees, and has much lower computation cost than the tree edit distance. In order to perform metric learning based on pq-grams, we propose a new differentiable parameterized distance, weighted pq-gram distance. We also propose a way to learn the proposed distance based on Large Margin Nearest Neighbors (LMNN), which is a well-studied and practical metric learning scheme. We formulate the metric learning problem as an optimization problem and use the gradient descent technique to perform metric learning. We empirically show that the proposed approach not only achieves competitive results with the state-of-the-art edit distance-based methods in various classification problems, but also solves the classification problems much more rapidly than the edit distance-based methods.

Neural machine translation models are used to automatically generate a document from given source code since this can be regarded as a machine translation task. Source code summarization is one of the components for automatic document generation, which generates a summary in natural language from given source code. This suggests that techniques used in neural machine translation, such as Long Short-Term Memory (LSTM), can be used for source code summarization. However, there is a considerable difference between source code and natural language: Source code is essentially structured, having loops and conditional branching, etc. Therefore, there is some obstacle to apply known machine translation models to source code.Abstract syntax trees (ASTs) capture these structural properties and play an important role in recent machine learning studies on source code. Tree-LSTM is proposed as a generalization of LSTMs for tree-structured data. However, there is a critical issue when applying it to ASTs: It cannot handle a tree that contains nodes having an arbitrary number of children and their order simultaneously, which ASTs generally have such nodes. To address this issue, we propose an extension of Tree-LSTM, which we call Multi-way Tree-LSTM and apply it for source code summarization. As a result of computational experiments, our proposal achieved better results when compared with several state-of-the-art techniques.

Extracting protein-protein interactions (PPIs) from articles is important in comprehending the underlying biological processes. With advances of natural language processing, many automatic PPI extraction methods from articles such as the machine learning-based methods, including the feature-based methods and the kernel-based ones, have been developed. However, the results of these methods still need to be improved much more. We propose a novel method to extract PPIs from articles. We use many diverse features, including lexical features obtained from sentences and features obtained from parse trees. We also devise new features extracted from shortest dependency paths obtained from dependency trees. In our method, after the training data and the test data are partitioned into subsets based on the basic structures of the sentences and the process of the feature selection (FS) is performed, we decrease the values of all the features, which belong to each group of similar features, of each instance by multiplying them with corresponding shrink coefficients of features. These shrink coefficients are determined automatically. Our experimental results using five corpora show the usefulness of the proposed method.

An overview of notable ILP areas, focusing on three invited talks at ILP 2015, two best student papers and the panel discussion on "ILP 25 Years".

Parameter tuning is essential in classification problems to achieve a high performance, but it is very hard when it comes to the one-class classification problem. In this paper, we propose a novel one-class classifier whose parameter can be tuned aut

We propose a new approach for semi-supervised learning using closed set lattices, which have been recently used for frequent pattern mining within the framework of the data analysis technique of Formal Concept Analysis (FCA). We present a learning al

We study the problem of mining closed frequent subtrees from tree databases that are updated regularly over time. Closed frequent subtrees provide condensed and complete information for all frequent subtrees in the database. Although mining closed frequent subtrees is in general faster than mining all frequent subtrees, this is still a very time consuming process, and thus it is undesirable to mine from scratch when the change to the database is small. The set of previous mined closed subtrees should be reused as much as possible to compute new emerging subtrees. We propose, in this paper, a novel and efficient incremental mining algorithm for closed frequent labeled ordered trees. We adopt a divide-and-conquer strategy and apply different mining techniques in different parts of the mining process. The proposed algorithm requires no additional scan of the whole database while its memory usage is reasonable. Our experimental study on both synthetic and real-life datasets demonstrates the efficiency and scalability of our algorithm.

We present in this paper a new clustering algorithm for multivariate data. This algorithm, called BOOL (Binary coding Oriented clustering), can detect arbitrarily shaped clusters and is noise tolerant. BOOL handles data using a two-step procedure: data points are first discretized and represented as binary words, clusters are then iteratively constructed by agglomerating smaller clusters using this representation. This latter step is carried out with linear complexity by sorting such binary representations, which results in dramatic speedups when compared with other techniques. Experiments show that BOOL is faster than K-means, and about two to three orders of magnitude faster than two state-of-the-art algorithms that can detect non-convex clusters of arbitrary shapes. We also show that BOOL's results are robust to changes in parameters, whereas most algorithms for arbitrarily shaped clusters are known to be overly sensitive to such changes. The key to the robustness of BOOL is the hierarchical structure of clusters that is introduced automatically by increasing the accuracy of the discretization.

This paper introduces the system on a chip (SOC) equipped with dual RISC processors, an image recognition engine operating with up to 55.3 GOPS, multiple accelerators and peripherals for car navigation systems. The SoC has high performance with respect to image recognition applications which are installed in advanced vehicles as well as navigation function such as graphics operating at the same time. Furthermore we have developed the SoC in order to meet automotive specifications including cost and size. We report practical application which is for the pedestrian detection to demonstrate our SoC capability. We accelerate the application with combination of the RISC processor and image recognition engine.

Sound source tracking is an important function for autonomous robots, because sound is omni-directional and independent of light. This paper presents a new approach to sound source tracking for mobile robots using auditory sensors. We consider a general type of two-wheeled mobile robot that has wide industrial applications. Because obstacle avoidance is also an indispensable function for autonomous mobile robots, the robot is equipped with distance sensors to detect obstacles in real time. To deal with the nonholonomic constraint of the robot and combine information from the auditory and distance sensors, we propose a model reference control approach in which the robot follows a desired trajectory generated by a reference model. The effectiveness of the proposed method is confirmed by experiments in which the robot is expected to approach a sound source while avoiding the obstacles.

A shape feature by itself is not sufficient for effective 3D model retrieval. Long-lasting semantics shared by a community as well as a short-lived intention of a user determines the similarity of 3D models. In this paper, we describe a method of shape-based 3D model retrieval that employs off-line, semi-supervised learning of multiple classes in the database to capture long-lasting, shared semantic knowledge. The method performs two learning based dimension reductions, first one to accommodate distribution of features in the feature space and the second one to accommodate the semantic knowledge embodied in a set of user-defined semantic labels. We evaluate the method by using the SHREC’08 3D Generic and CAD Models Track.

We propose two methods of digital watermark for image signals based on the wavelet transform. We classify wavelet coefficients as insignificant or significant by using zerotree which is defined in the embedded zerotree wavelet (EZW) algorithm. In the first method, information data are embedded as a watermark in the location of insignificant coefficients. In the second method, information data can be embedded by thresholding and modifying significant coefficients at the coarser scales in perceptually important spectral components of image signals. Information data are detected by using the position of zerotree's root and the threshold value after the wavelet decomposition of an image in which data hide. Experimental results show the proposed method gives the watermarked image of better quality and is robust against JPEG compression.

Points out that scan design approach is representative of those techniques that can reduce the cost of test generation for sequential circuits. However, the length of a test sequence for the scan design approach can grow quite large due to the scan operation shifting the values into the scan chain, which makes the cost of test application large. A design-for-testability approach called parity-scan design which can reduce the cost of test application as well as the cost of test generation for sequential circuits is discussed. The parity-scan design approach is a combination of scan technique and parity testing. Two types of parity-scan designs, preparity and postparity scan design, are presented. Experiments on ISCAS89 circuits show that as high as 91.2% (91.1%) test length reduction and 32.4% (27.0%) average reduction can be obtained for preparity (postparity) scan design under the single scan chain approach. More reduction can be achieved by applying a multiple scan chain technique.>

Points out that scan design approach is representative of those techniques that can reduce the cost of test generation for sequential circuits. However, the length of a test sequence for the scan design approach can grow quite large due to the scan operation shifting the values into the scan chain, which makes the cost of test application large. A design-for-testability approach called parity-scan design which can reduce the cost of test application as well as the cost of test generation for sequential circuits is discussed. The parity-scan design approach is a combination of scan technique and parity testing. Two types of parity-scan designs, preparity and postparity scan design, are presented. Experiments on ISCAS89 circuits show that as high as 91.2% (91.1%) test length reduction and 32.4% (27.0%) average reduction can be obtained for preparity (postparity) scan design under the single scan chain approach. More reduction can be achieved by applying a multiple scan chain technique. >