Subscribe: Computational Intelligence Magazine, IEEE - new TOC
http://ieeexplore.ieee.org/rss/TOC10207.XML
Preview: Computational Intelligence Magazine, IEEE - new TOC

IEEE Computational Intelligence Magazine - new TOC



TOC Alert for Publication# 10207



 



Front Cover

Aug. 2017

Presents the front cover for this issue of the publication.



IEEE WCCI 2018

Aug. 2017

Describes the above-named upcoming conference event. May include topics to be covered or calls for papers.



Table of Contents

Aug. 2017

Presents the table of contents for this issue of the publication.



CIM Editorial Board

Aug. 2017

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.



After 30 Years of Work in Osaka [Editor's Remarks]

Aug. 2017

Presents the introductory editorial for this issue of the publication.



SSCI2017

Aug. 2017

Describes the above-named upcoming conference event. May include topics to be covered or calls for papers.



Ethics and the Social Impact of Computational Intelligence [President's Message]

Aug. 2017

At the time of writing this column, I have just finished a tour in Chile & Argentina with the Executive Committee (EXCOM) of the IEEE Computational Intelligence Society (CIS). As part of our geographical outreach program we organized CIS workshops at La Serena University, in northern Chile; the University of Chile, in Santiago; and the University of Buenos Aires, in Argentina. In Chile we had the opportunity to visit the astronomy observatories located near La Serena. Dr. Chris Smith, an astronomer and the head of mission, AURA Observatory in Chile, was our knowledgeable host. The actual telescope sites are located in an area of more than 90,000 acres that includes two operational mountaintops, Cerro Tololo at 2,200 m, and Cerro Pachon at 2,750 m. Tololo is a very famous place, because the discovery of the accelerated expansion of the Universe was made in these facilities. Pachon is the place where the new generation telescope named LSST is being built.



CIS Society Officers

Aug. 2017

Presents a listing of CIS society officers.



CIS Publication Spotlight [Publication Spotlight]

Aug. 2017

Presents a synopsis of the latest books in the area of computational intelligence.



Natural Language Generation with Computational Intelligence [Guest Editorial]

Aug. 2017

The articles in this special section focus on using natural language generation techniques (NLG) and natural language processing (NLP) to build computational systems that generate reports and other kinds of text in human languages. NLG uses analytics, AI, and NLP to obtain relevant information about non-linguistic data and to generate textual summaries and explanations of these data which help people understand and benefit from them. In this regard, NLG is a research field that addresses the data-value chain by using natural language as a tool for bridging the gap between raw data and valuable information communicated to users in a comprehensible way, adapted to their information needs.



Data-to-Text Generation Improves Decision-Making Under Uncertainty

Aug. 2017

Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores or probabilities. This article presents a comparison of different information presentations for uncertain data and, for the first time, measures their effects on human decision-making, in the domain of weather forecast generation. We use a game-based setup to evaluate the different systems. We show that the use of Natural Language Generation (NLG) enhances decision-making under uncertainty, compared to state-of-the-art graphical-based representation methods. In a task-based study with 442 adults, we found that presentations using NLG led to 24% better decision-making on average than the graphical presentations, and to 44% better decision-making when NLG is combined with graphics. We also show that women achieve significantly better results when presented with NLG output (an 87% increase on average compared to graphical presentations). Finally, we present a further analysis of demographic data and its impact on decision-making, and we discuss implications for future NLG systems.



Domain Transfer for Deep Natural Language Generation from Abstract Meaning Representations

Aug. 2017

Stochastic natural language generation systems that are trained from labelled datasets are often domain-specific in their annotation and in their mapping from semantic input representations to lexical-syntactic outputs. As a result, learnt models fail to generalize across domains, heavily restricting their usability beyond single applications. In this article, we focus on the problem of domain adaptation for natural language generation. We show how linguistic knowledge from a source domain, for which labelled data is available, can be adapted to a target domain by reusing training data across domains. As a key to this, we propose to employ abstract meaning representations as a common semantic representation across domains. We model natural language generation as a long short-term memory recurrent neural network encoder-decoder, in which one recurrent neural network learns a latent representation of a semantic input, and a second recurrent neural network learns to decode it to a sequence of words. We show that the learnt representations can be transferred across domains and can be leveraged effectively to improve training on new unseen domains. Experiments in three different domains and with six datasets demonstrate that the lexical-syntactic constructions learnt in one domain can be transferred to new domains and achieve up to 75-100% of the performance of in-domain training. This is based on objective metrics such as BLEU and semantic error rate and a subjective human rating study. Training a policy from prior knowledge from a different domain is consistently better than pure in-domain training by up to 10%.



Learning to Generate Descriptions of Visual Data Anchored in Spatial Relations

Aug. 2017

The explosive growth of visual data both online and offline in private and public repositories has led to urgent requirements for better ways to index, search, retrieve, process and manage visual content. Automatic methods for generating image descriptions can help with all these tasks, and also play an important role in assistive technology for the visually impaired. The task we address in this paper is the automatic generation of image descriptions that are anchored in spatial relations. We construe this as a three-step task where the first step is to identify objects in an image, the second step detects spatial relations between object pairs on the basis of language and visual features; and in the third step, the spatial relations are mapped to natural language (NL) descriptions. We describe the data we have created, and compare a range of machine learning methods in terms of the success with which they learn the mapping from features to spatial relations, using automatic and human-assessed evaluations. We find that a random forest model performs best by a substantial margin. We examine aspects of our approach in more detail, including data annotation and choice of features. We describe six alternative natural language generation (NLG) strategies, and evaluate the generated NL strings using measures of correctness, naturalness and completeness. Finally, we discuss evaluation issues, including the importance of extrinsic context in data creation and evaluation design.



Pattern Recommendation in Task-oriented Applications: A Multi-Objective Perspective [Application Notes]

Aug. 2017

Task-oriented pattern mining is to find the most popular and complete pattern for task-oriented applications such as goods match recommendation and print area recommendation. In these applications, the measure support is used to capture the popularity of patterns, while the measure occupancy is adopted to capture the completeness of patterns. Existing methods for mining task-oriented patterns usually combine these two measures as one measure for optimization, and require users to set the prior parameters such as the minimum support threshold min_sup, the minimum occupancy threshold min_occ and the relative importance preference λ between support and occupancy. However, it is very difficult for users to set optimal values for these parameters especially when they do not have any prior knowledge in real applications. To overcome this challenge, we propose an evolutionary approach for pattern mining from a multi-objective perspective since support and occupancy are conflicting. Specifically, we first transform this pattern mining problem into a multi-objective optimization problem. Then we propose an effective multi-objective pattern mining evolutionary algorithm for finding optimal pattern set, which does not need to specify the prior parameters min_sup, min_occ and m. Finally, we select k best patterns from the obtained pattern set for final pattern recommendation. Experimental results on two real task-oriented applications, namely, goods match recommendation in Taobao and print area recommendation in SmartPrint, and several large synthetic datasets demonstrate the promising performance of the proposed method in terms of both effectiveness and efficiency.



Gene Expression Programming: A Survey [Review Article]

Aug. 2017

Abstract Gene Expression Programming (GEP) is a popular and established evolutionary algorithm for automatic generation of computer programs. In recent decades, GEP has undergone rapid advancements and developments. A number of enhanced GEPs have been proposed to date and the real world applications that use them are also multiplying fast. In view of the steadfast growth of GEP and its importance to both the academia and industry, here a review on GEP is considered. In particular, this paper presents a comprehensive review on the recent progress of GEP. The state-of-the-art approaches of GEP, with enhanced designs from six aspects, i.e., encoding design, evolutionary mechanism design, adaptation design, cooperative co-evolutionary design, constant creation design, and parallel design, are presented. The theoretical studies and intriguing representative applications of GEP are given. Finally, a discussion of potential future research directions of GEP is also provided.






[Conference Calendar]

Aug. 2017

Presents the CIS society calendar of upcoming events and meetings.



Call for Papers for Journal Special Issues

Aug. 2017

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal.



CIG 2018

Aug. 2017

Describes the above-named upcoming conference event. May include topics to be covered or calls for papers.



SSCI2018

Aug. 2017

Describes the above-named upcoming conference event. May include topics to be covered or calls for papers.