Dynamic multi-relational Chinese restaurant process for analyzing influences on users in social media

We study the problem of analyzing influence of various factors affecting individual messages posted in social media. The problem is challenging because of various types of influences propagating through the social media network that act simultaneously on any user. Additionally, the topic composition of the influencing factors and the susceptibility of users to these influences evolve over time. This problem has not been studied before, and off-the-shelf models are unsuitable for this purpose. To capture the complex interplay of these various factors, we propose a new non-parametric model called the Dynamic Multi-Relational Chinese Restaurant Process. This accounts for the user network for data generation and also allows the parameters to evolve over time. Designing inference algorithms for this model suited for large scale social-media data is another challenge. To this end, we propose a scalable and multi-threaded inference algorithm based on online Gibbs Sampling. Extensive evaluations on large-scale Twitter and Face book data show that the extracted topics when applied to authorship and commenting prediction outperform state-of-the-art baselines. More importantly, our model produces valuable insights on topic trends and user personality trends beyond the capability of existing approaches.

Exploiting Chinese character models to improve speech recognition performance

The Chinese language is based on characters which are syllabic in nature. Since languages have syllabotactic rules which govern the construction of syllables and their allowed sequences, Chinese character sequence models can be used as a first level approximation of allowed syllable sequences. N-gram character sequence models were trained on 4.3 billion characters. Characters are used as a first level recognition unit with multiple pronunciations per character. For comparison the CU-HTK Mandarin word based system was used to recognize words which were then converted to character sequences. The character only system error rates for one best recognition were slightly worse than word based character recognition. However combining the two systems using log-linear combination gives better results than either system separately. An equally weighted combination gave consistent CER gains of 0.1-0.2% absolute over the word based standard system. Copyright © 2009 ISCA.

Ancient Chinese algorithm: The Ying Buzu Shu (method of surplus and deficiency) vs Newton iteration method

Air exploratory discussion of an ancient Chinese algorithm, the Ying Buzu Shu, in about 2nd century BC, known as the rule of double false position in the West is given. In addition to pointing out that the rule of double false position is actually a translation version of the ancient Chinese algorithm, a comparison with well-known Newton iteration method is also made. If derivative is introduced, the ancient Chinese algorithm reduces to the Newton method. A modification of the ancient Chinese algorithm is also proposed, and some of applications to nonlinear oscillators are illustrated.

Chinese Texts Progress Report

Progress report for the Chinese Texts, Digging into Data Challenge round 3, project.

中国力学学会史 = A history of Chinese society of theoretical and applied mechanics

《中国力学学会史》是《中国学会史丛书》之一。是一部全面系统记述中国力学学会建立与发展历程的专著。 《中国力学学会史》全书30万字，书中不但重点对学会的初创情况、发展过程、组织建设、学术交流、分支机构等进行了专门介绍，还特别收录了记述学会重大活动情况的大事记、名人与学会发展的丰富资料和一些极有史料价值的历史照片，旨在反映学会在不同时期的活动概况及其在中国力学界中发挥的桥梁与纽带作用。 中国力学学会是中国科协的组成部分，也是我国著名的学术团体之一，仅以此书的编著出版，纪念中国科协成立50周年和中国力学学会成立50多周年。本书可供力学界和科技界有关部门及工作者、各学会相关人员、大专院校师生参阅，也可作为组织和开展国内外学术交流研究的参考资料。

Compression of Chinese document images based on morphologic analysis and pattern matching

We propose a highly efficient content-lossless compression scheme for Chinese document images. The scheme combines morphologic analysis with pattern matching to cluster patterns. In order to achieve the error maps with minimal error numbers, the morphologic analysis is applied to decomposing and recomposing the Chinese character patterns. In the pattern matching, the criteria are adapted to the characteristics of Chinese characters. Since small-size components sometimes can be inserted into the blank spaces of large-size components, we can achieve small-size pattern library images. Arithmetic coding is applied to the final compression. Our method achieves much better compression performance than most alternative methods, and assures content-lossless reconstruction. (c) 2006 Society of Photo-Optical Instrumentation Engineers.