Computational and Quantitative Studies

William C. Mann passed away on August 13, 2004, after a long struggle with leukemia. He is known to readers of Computational Linguistics as a keen supporter and past president (1987) of ACL, a pioneer in the development of text generation as a field of research in computational linguistics, the originator of rhetorical structure theory (RST) and dialogue game theory (DGT), and the developer (together with David Weber) of dialect adaptation as a technique within machine translation. And he’ll be remembered for these and many other contributions, but above all, in this context, he’ll be remembered as a unique visionary in computational linguistics (CL) and as a truly wonderful and extraordinarily generous colleague. Bill Mann made huge contributions to many people’s intellectual development, to their careers, and to their lives in general. What follows are my own recollections of him, selected from a crowded jungle of memories. I will leave it to others to fill out the picture, but I shall attempt to give an indication of the intellectual and historical context in which Bill was working and also of the network of researchers that he created; his ideas have radiated throughout this network of scholars around the world. I met Bill in April 1980 and worked as a research linguist on a succession of projects he directed, or codirected, at the Information Sciences Institute (ISI) at the University of Southern California (USC), until I left the institute to take up a position at the University of Sydney in August 1988. Through that period (which happened to coincide, more or less, with the Reagan years), not only was Bill a very wise and wonderful project leader, but he also became a mentor and guide and a true friend. I followed from afar the further developments in his life: his departure from ISI and move to Kenya with his family to take up a position with the Summer Institute of Linguistics (SIL) as a consultant responsible for work on discourse and computational matters, their return to the United States, and his new phase of research with initiatives in RST and DGT.

Frontiers Events is a rapidly growing calendar management system dedicated to the scheduling of academic events. This includes announcements and invitations, participant listings and search functionality, abstract handling and publication, related events and post-event exchanges. Whether an organizer or participant, make your event a Frontiers Event!

AffiliationsJon-Patrick Allem is with the Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles. Emilio Ferrara is with the Information Sciences Institute, University of Southern California, Marina del Rey.

Computational intelligence is a modern research orientation to ensure effective and efficient outcomes for real world problems. As it is highly associated with essentials of statistics, data analytics, and artificial intelligence, technical fields have been intensively focused on using specific techniques to solve different problems. However, predictive analysis has been a modern solution approach for different aspects of advanced problems. Engineering-related applications find computational intelligence techniques useful to have desired outcomes at the end. Among the associated technical issues, Concrete technology finds its way by raising different issues and combining already known methods with the support of computational intelligence. This chapter provides a brief review of computational intelligence techniques to be used in concrete technology. The introduction is related to applications of predicting compressive strength and the ultrasonic pulse velocity. In this chapter, an overview of this book is provided. As an editorial introduction, remarkable original content texts by the book authors are combined in order to provide the most essential knowledge for the readers.

Jihie Kim is the Principal Investigator of the Intelligent Technologies for Teaching and Learning group in the USC Information Sciences Institute (http://ai.isi.edu/pedtek). She is also a Research Assistant Professor in the Computer Science Department at the University of Southern California (USC). Dr. Kim received a Ph.D. from the USC, and a master’s and a bachelor’s degrees from the Seoul National University.

The authors explore three topics in computational intelligence: machine translation, machine learning and user interface design and speculate on their effects on Web intelligence. Systems that can communicate naturally and learn from interactions will power Web intelligence's long term success. The large number of problems requiring Web-specific solutions demand a sustained and complementary effort to advance fundamental machine-learning research and incorporate a learning component into every Internet interaction. Traditional forms of machine translation either translate poorly, require resources that grow exponentially with the number of languages translated, or simplify language excessively. Recent success in statistical, nonlinguistic, and hybrid machine translation suggests that systems based on these technologies can achieve better results with a large annotated language corpus. Adapting existing computational intelligence solutions, when appropriate for Web intelligence applications, must incorporate a robust notion of learning that will scale to the Web, adapt to individual user requirements, and personalize interfaces.

Parallel machine translation (PMT) is a new machine translation paradigm that takes advantage of high-speed and large-memory computers and existing machine translation systems with different characteristics to solve the difficult machine translation problem. PMT is based on technologies of parallel computing, machine translation, and artificial intelligence. A PMT system consists of many machine translation procedures running in parallel, coordinated by a controller to dissolve various ambiguities in machine translation. We have designed and implemented a PMT system based on the above approach at a coarse parallel level. The system consists of four independent machine translation subsystems. Each subsystem is implemented using an existing machine translation technique and has its own characteristics. We present the principles and practice of PMT. We also present some results of experiments with our experimental PMT system and point out some future research on PMT.

It is proposed to get the fundamental theory of intelligent information processing with combining natural language understanding and computational intelligence. Considering applied fields on intelligent classification, indexing, retrieval, abstract and machine translation, natural language understanding can provide theoretical framework and computational intelligence will give technical realization.

The Seventh International Symposium on Neural Networks (ISNN 2010) was held on June 6–9, 2010 in Shanghai, China. The ISNN 2010 was a great success and provided a high-level international forum for scientists and engineers to present the latest research in neural networks, computational intelligence, cognitive systems, and related fields. To highlight the success of this conference, we edited this special issue for Cognitive Computation. We chose nine papers from over 591 papers submitted to ISNN 2010, which reflect the high quality of the presentations at the conference while capturing the spirit of our theme, ‘‘Advances in Computational Intelligence and Applications,’’ for this special issue. Our goal for this special issue is to present the latest research developments in computational intelligence with a focus on cognitive computation and their applications across a wide range of domains. Over the past decades, we have witnessed tremendous interest and developments in all aspects of computational intelligence research, ranging from both theoretical foundations, principles, to practical applications in different domains. To reflect a flavor of recent research activities in the community, we carefully selected these nine papers for this special issue. The selected papers can be organized into the following four coherent sections. The first section is directly related to neural network models and applications. The paper by Deng presents a new control strategy for the chaotic neural network, in which the refractoriness is tuned by using feedback control based on online averaging of network states. Simulation results demonstrate that the proposed model can achieve favorable performance in handling noisy, incomplete, and composite patterns, while also achieving either enhanced or comparable memory capacity compared with the classic Hopfield net and other chaotic neural network models. In the other paper, Gluge et al. discuss recurrent networks for implicit learning of temporal sequences, a very important area to understand high-level cognitive intelligence. The authors propose a recurrent network with backpropagation training algorithm that is adapted to the reinforcement learning scheme. The simulation results fit quantitatively as well as qualitatively to the behavioral results, suggesting the role of temporal context in associative learning scenarios. The second section is related to language processing and understanding, an important topic in cognitive science and computational intelligence. The paper by Murata et al. investigates the maximum entropy (ME) approach for natural language processing (NLP) problems including machine translation and information extraction. Comparative studies of the proposed approach with the existing techniques are illustrated in this paper. In related work to this field, the paper by Kaznatcheev investigates connectionist models on the interplay of nouns and pronouns in personal pronoun acquisition, a very interesting and important problem in psychology. For instance, the author discusses the learning in the shifting reference situation for children. It is reported that learning of two different noun-and-pronoun addressee patterns is consistent with Z. Zeng (&) Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, P. R. China e-mail: zgzeng@gmail.com

Syntax-based statistical machine translation (MT) aims at applying statistical models to structured data. In this paper, we present a syntax-based statistical machine translation system based on a probabilistic synchronous dependency insertion grammar. Synchronous dependency insertion grammars are a version of synchronous grammars defined on dependency trees. We first introduce our approach to inducing such a grammar from parallel corpora. Second, we describe the graphical model for the machine translation task, which can also be viewed as a stochastic tree-to-tree transducer. We introduce a polynomial time decoding algorithm for the model. We evaluate the outputs of our MT system using the NIST and Bleu automatic MT evaluation software. The result shows that our system outperforms the baseline system based on the IBM models in both translation speed and quality.

Palash Goyal is a Senior Research Scientist at Samsung Research America. In 2019, he got his doctoral degree in Computer Science from University of Southern California under the advisory of Dr. Emilio Ferrara. Over the course of his PhD, he worked with several government funded projects including IARPA and DARPA spanning domains of time series prediction, text analysis and understanding social behavior. He also applied his work on graph embedding in various industrial settings including developing automation systems in Siemens Corporate, identifying key steam injection candidate oil wells for Chevron and developing recommendation system for Target. His work on tracking temporal evolution of graphs using non-timestamped data was nominated for best paper award in ACM Hypertext. In his thesis, supervised by Dr. Emilio Ferrara (USC Information Sciences Institute), he ex- tended the work of learning low-dimensional representations of nodes in a graph in several di- rections. Firstly, he published a survey of existing graph embedding approaches and shed light into the dependency between them drawing insights into the relations effectively captured by the methods. He further proposed a benchmark to evaluate any graph embedding approach and un- derstand its applicability. Secondly, he built models to capture temporal patterns in sequential graphs and efficiently update embeddings for streaming graphs. Finally, he developed multi-modal models for learning representations through graph data as well as other forms of data available for the nodes and edges including text.

The MOSIS Service at the University of Southern California's Information Sciences Institute offers services to obtain custom designed prototype quantities of ASICs and Multichip Modules (MCMs). The service recently added MIDAS, the MultiChip Module Designers' Access Service for MCM fabrication to the list of standard offerings. Thus a designer can now access domestic, high-volume IC and MCM production lines to obtain low-cost, prototype quantities of both. The low-cost environment exists via a multi-project environment, where users share the cost of NRE, masks, and fabrication. MOSIS takes care of front end foundry tasks such as data preparation and obtaining masks as well as placing the orders and delivering the finished product. This paper discusses how to access MOSIS to obtain custom ICs and MCMs for building innovative microelectronic devices.

This is a time that poses numerous challenges to urban geographers and the cities they study. As it happens, 2004 was a period of disciplinary reflection marking the centennial of the Association of American Geographers (AAG). As graduate student members of the board of the AAG’s Urban Geography Specialty Group, we capitalized on a confluence of events to organize a panel entitled “The state of urban geography: What is it and where is it going?” for the AAG’s 2004 annual meeting in Philadelphia. This year of disciplinary celebration also coincided with the torment of our own early professional lives as newly-minted, so-called urban geographers. Drawn into collaboration through these circumstances, we chose to organize a session in which we invited urban geographers at various stages in their careers to reflect on the subdiscipline and its practice. To initiate dialogue, we asked: What is the significance of the subdiscipline to the production and application of geographic knowledge? What—or who—defines urban geography? Is urban geography what urban geographers do or is it something more? To be sure, the forward-looking spirit of the day fulfilled our initial hopes. We were fortunate to assemble an impressive set of urban geographers with diverse interests and experiences, including Larry Bourne (University of Toronto), Winifred Curran (DePaul University), Michael Dear (University of Southern California), Sarah Elwood (University of Arizona), Robert Lake (Rutgers University), and Sallie Marston (University of Arizona). Some panelists were close to retirement and others were equally close to the start of a new job. The group spoke to a standing-room-only crowd about their accomplishments, their hopes for, and their disappointments with urban geography at the turn of the millennium. When invited to assemble and introduce the panelists’ reflections as a symposium for this journal, we relished our own opportunity to ponder the state of the subdiscipline. But

This study aims to examine trends and future tasks of the Korean language education researches which use quantitative research methods and quantitative analysis in particular. In this study quantitative research methods are understood as statistical analysis-based research methods. In the quantitative analysis-based researches numerical materials are collected (characteristic aspect of the materials) and the materials are processed using statistical methods (processing aspect of the materials). The following points are examined. Firstly, a problem of subclassification of the quantitative method-based Korean language education researches is dealt with. Secondly, the two aspects, i.e. the collection of numerical materials in the Korean language education researches and the statistical processing of them are presented and a typical order of their statistical processing is examined. Thirdly, a problem of the quantitative indicator playing an important role in the collection of quantified materials is examined. The problem refers to what kind of quantitative indicators are used in corpus studies, and what kind of studies can be used in order to implement new quantitative indicators. Lastly, the study is concluded with a question on how the quantitative studies should deal with criticism on the quantitative analysis-based studies stating that the studies conducted in an artificial environment with restricted variables have difficulties in properly explaining complicated teaching-learning conditions. In order to examine recent trends in the quantitative analysis-based Korean language education studies this study examined research methods used in articles from three academic journals on Korean language education published in the last five years (from 2010 to September 2015). The examination revealed that 185 papers used quantitative analysis. Among them studies utilizing descriptive statistics were most common. In case of studies utilizing inferential statistics, comparative studies verifying differences between groups or variables, correlative studies showing relations between variables, effect relationship studies showing effect relations between variables and classification studies classifying variables or groups were distinguished.

Recently Published Dissertations on Community and Junior Colleges