The Meteor metric for automatic evaluation of machine translation

The Meteor Automatic Metric for Machine Translation evaluation, originally developed and released in 2004, was designed with the explicit goal of producing sentence-level scores which correlate well with human judgments of translation quality. Several key design decisions were incorporated into Meteor in support of this goal. In contrast with IBM’s Bleu, which uses only precision-based features, Meteor uses and emphasizes recall in addition to precision, a property that has been confirmed by several metrics as being critical for high correlation with human judgments. Meteor also addresses the problem of reference translation variability by utilizing flexible word matching, allowing for morphological variants and synonyms to be taken into account as legitimate correspondences. Furthermore, the feature ingredients within Meteor are parameterized, allowing for the tuning of the metric’s free parameters in search of values that result in optimal correlation with human judgments. Optimal parameters can be separately tuned for different types of human judgments and for different languages. We discuss the initial design of the Meteor metric, subsequent improvements, and performance in several independent evaluations in recent years.     

More on graph theoretic software watermarks: Implementation,analysis, and attacks

This paper presents an implementation of the watermarking method proposed by Venkatesan et al. in their paper [R. Venkatesan, V. Vazirani, S. Sinha, A graph theoretic approach to software watermarking, in: Fourth International Information Hiding Workshop, Pittsburgh, PA, 2001]. An executable program is marked by the addition of code for which the topology of the control-flow graph encodes a watermark. We discuss issues that were identified during construction of an actual implementation that operates on Java bytecode. We present two algorithms for splitting a watermark number into a redundant set of pieces and an algorithm for turning a watermark number into a control-flow graph. We measure the size and time overhead of watermarking, and evaluate the algorithm against a variety of attacks.     

On the classification performance of TAN and general Bayesian networks

Over a decade ago, Friedman et al. introduced the Tree Augmented Naïve Bayes (TAN) classifier, with experiments indicating that it significantly outperformed Naïve Bayes (NB) in terms of classification accuracy, whereas general Bayesian network (GBN) classifiers performed no better than NB. This paper challenges those claims, using a careful experimental analysis to show that GBN classifiers significantly outperform NB on datasets analyzed, and are comparable to TAN performance. It is found that the poor performance reported by Friedman et al. are not attributable to the GBN per se, but rather to their use of simple empirical frequencies to estimate GBN parameters, whereas basic parameter smoothing (used in their TAN analyses but not their GBN analyses) improves GBN performance significantly. It is concluded that, while GBN classifiers may have some limitations, they deserve greater attention, particularly in domains where insight into classification decisions, as well as good accuracy, is required.     

Thermal and cardiovascular strain imposed by motorcycle protective clothing under Australian summer conditions

Motorcycle protective clothing can be uncomfortably hot during summer, and this experiment was designed to evaluate the physiological significance of that burden. Twelve males participated in four, 90-min trials (cycling 30 W) across three environments (25, 30, 35 °C [all 40% relative humidity]). Clothing was modified between full and minimal injury protection. Both ensembles were tested at 25 °C, with only the more protective ensemble investigated at 30 and 35 °C. At 35 °C, auditory canal temperature rose at 0.02 °C min^?1 (SD 0.005), deviating from all other trials (p < 0.05). The thresholds for moderate (>38.5 °C) and profound hyperthermia (>40.0 °C) were predicted to occur within 105 min (SD 20.6) and 180 min (SD 33.0), respectively. Profound hyperthermia might eventuate in ~10 h at 30 °C, but should not occur at 25 °C. These outcomes demonstrate a need to enhance the heat dissipation capabilities of motorcycle clothing designed for summer use in hot climates, but without compromising impact protection.

Practitioner’s Summary:

Motorcycle protective clothing can be uncomfortably hot during summer. This experiment was designed to evaluate the physiological significance of this burden across climatic states. In the heat, moderate (>38.5 °C) and profound hyperthermia (>40.0 °C) were predicted to occur within 105 and 180 min, respectively.     

Creating the Enabling Environment for More Transparent and Better-resourced Local Governments: A Case of E-taxation in the Philippines

This research joins the growing body of literature that advocates for the use of information and communication technology (ICT) in local governance more particularly in public financial management. Using a case study in Bohol, a province in the Philippines, this paper discusses the impact of ICT on local revenue generation by analyzing both quantitative and qualitative data from 15 municipalities which used e-taxation. This paper argues that the use of ICT can make possible more transparent and accountable revenue generation systems to benefit both government and taxpayers. However, these results are differentiated depending on the level of political leadership, the nature of articulation of the demand for ICT use, the ratio of benefit against cost, and the availability of technical skills and resources at the sub-national level. It is within this context that an eco-system analysis is argued to be useful in analyzing how ICT can be adopted, scaled, and used by sub-national governments to achieve better governance.     

VerifyThis 2015

VerifyThis 2015 was a one-day program verification competition which took place on April 12th, 2015 in London, UK, as part of the European Joint Conferences on Theory and Practice of Software (ETAPS 2015). It was the fourth instalment in the VerifyThis competition series. This article provides an overview of the VerifyThis 2015 event, the challenges that were posed during the competition, and a high-level overview of the solutions to these challenges. It concludes with the results of the competition and some ideas and thoughts for future instalments of VerifyThis.     

Distraction 'on the buses': a novel framework of ergonomics methods for identifying sources and effects of bus driver distraction

Driver distraction represents a significant problem in the public transport sector. Various methods exist for investigating distraction; however, the majority are difficult to apply within the context of naturalistic bus driving. This article investigates the nature of bus driver distraction at a major Australian public transport company, including the sources of distraction present, and their effects on driver performance, through the application of a novel framework of ergonomics methods. The framework represents a novel approach for assessing distraction in a real world context. The findings suggest that there are a number of sources of distraction that could potentially distract bus drivers while driving, including those that derive from the driving task itself, and those that derive from the additional requirements associated with bus operation, such as passenger and ticketing-related distractions. A taxonomy of the sources of bus driver distraction identified is presented, along with a discussion of proposed countermeasures designed to remove the sources identified or mitigate their effects on driver performance.     

On event design in event-triggered feedback systems

This paper studies event design in event-triggered feedback systems. A novel event-triggering scheme is presented to ensure exponential stability of the resulting sampled-data system. The scheme postpones the triggering of events over previously proposed methods and therefore enlarges the intersampling period. The resulting intersampling periods and deadlines are bounded strictly away from zero when the continuous time system is input-to-state stable with respect to measurement errors.     

On designing safe and flexible embedded DSLs with Java 5

Although embedded DSLs are widely used in both functional and dynamic languages they are yet to be widely accepted in the Java community. The best available examples are projects like jMock and Hibernate Criteria Query. In this paper we introduce the design of three novel practical embedded DSLs that we designed to showcase the power of Java language and specifically the changes introduced in Java 5. One of those DSLs is fully implemented as an open source project and is gathering momentum in the community. We proceed to discuss the approaches that allow designing safe and flexible DSLs by extracting generic patterns where possible and describing more specific idioms where necessary. It is our goal that this paper would serve as a starting point for someone designing an embedded DSL that takes full advantage of the Java 5 features.