Automatic Composition of Encoding Scheme and Search Operators in System Architecture Optimization

The purpose of this paper is to propose a new method for the automatic composition of both encoding schemes and search operators for system architecture optimization. The method leverages prior work that identified a set of six patterns that appear often in system architecture decision problems (down-selecting, combining, assigning, partitioning, permuting, and connecting). First, the user models the architecture space as a directed graph, where nodes are decisions belonging to one of the aforementioned patterns, and edges are dependencies between decisions that affect architecture enumeration (e.g., the outcome of decision 1 affects the number of alternatives available for decision 2). Then, based on a library of encoding scheme and operator fragments that are appropriate for each pattern, an algorithm automatically composes an encoding scheme and corresponding search operators by traversing the graph. The method is demonstrated in two case studies: a study integrating three architectural decisions for constructing a portfolio of earth observing satellite missions, and a study integrating eight architectural decisions for designing a guidance navigation and control system. Results suggest that this method has comparable search performance to hand-crafted formulations from experts. Furthermore, the proposed method drastically reducing the need for practitioners to write new code.

A roadmap toward the automatic composition of systematic literature reviews

Objective. This paper presents an overview of existing artificial intelligence tools to produce systematic literature reviews. Furthermore, we propose a general framework resulting from combining these techniques to highlight the challenges and possibilities currently existing in this research area. Design/Methodology/Approach. We undertook a scoping review on the systematic literature review steps to automate them via computational techniques. Results/Discussion. The process of creating a literature review is both creative and technical. The technical part of this process is liable to automation. Based on the literature, we chose to divide this technical part into four steps: searching, screening, extraction, and synthesis. For each one of these steps, we presented practical artificial intelligence techniques to carry them out. In addition, we presented the obstacles encountered in the application of each technique. Conclusion. We proposed a framework for automatically creating systematic literature reviews by combining and placing existing techniques in stages where they possess the greatest potential to be useful. Despite still lacking practical assessment in different areas of knowledge, this proposal indicates ways with the potential to reduce the time-consuming and repetitive work embedded in the systematic literature review process. Originality/Value. The paper presents the current possibilities for automating systematic literature reviews and how they can work together to reduce researchers’ operational workload.

From Artificial to Extended Intelligence in Music Composition

This article explores the relationship and disparities between human and computational creativity by addressing the following questions: How well are computational creativity systems currently performing at creative tasks? Could computers outperform human composers? And, if not, is computational creativity a utopia? Automatic composition systems are examined with respect to Boden’s three criteria of creativity (novelty, surprise and value), as well as their assumptions about the nature of creativity. As an alternative to a competitive relationship between human and computational creativity, the article proposes the concept of a distributed human–computer co-creativity, in which computational creativity extends – rather than replaces – human creativity, by expanding the space of creative possibilities.

A Neural Network Approach to Verb Phrase Ellipsis Resolution

Verb Phrase Ellipsis (VPE) is a linguistic phenomenon, where some verb phrases as syntactic constituents are omitted and typically referred by an auxiliary verb. It is ubiquitous in both formal and informal text, such as news articles and dialogues. Previous work on VPE resolution mainly focused on manually constructing features extracted from auxiliary verbs, syntactic trees, etc. However, the optimization of feature representation, the effectiveness of continuous features and the automatic composition of features are not well addressed. In this paper, we explore the advantages of neural models on VPE resolution in both pipeline and end-to-end processes, comparing the differences between statistical and neural models. Two neural models, namely multi-layer perception and the Transformer, are employed for the subtasks of VPE detection and resolution. Experimental results show that the neural models outperform the state-of-the-art baselines in both subtasks and the end-to-end results.