This paper presents the results of the WMT14 Metrics Shared Task. We asked participants of this task to score the outputs of the MT systems involved in WMT14 Shared Translation Task. We collected scores of 23 metrics from 12 research groups. In addition to that we computed scores of 6 standard metrics (BLEU, NIST, WER, PER, TER and CDER) as baselines. The collected scores were evaluated in term...

This work refers to the review of 258 papers published in the WER throughout 15 editions. This review ́s goal was to identify the most active research groups within this workshop, the most debated topics and the trends in the Requirements Engineering area. The results showed that Brazil, Argentina and Spain hold the most active groups. Moreover, the results pointed out the requirements modeling ...

Background & Aims of the Study: Reporting human errors in healthcare agencies is often accompanied by embarrassment and the fear of punishment; such errors can highlight motivation, the lack of attention, and enough education. Thus, there is a tendency to hide them. This study aimed to investigate the barriers and facilitators of reporting medical errors in hospitals. Materials and Methods:...

Background Medication errors (MEs) are the most common types of medical errors which effecting on pediatric safety. For decrease MEs, we should to have information about difference aspects of MEs. We have no study which assessed the frequency, types and causes of MEs made by pediatric nurses, in Iran. Material and Methods This was a cross-sectional study, which performed on 53 Pediatric Nurses....

In this paper we show how methods for approximating phone error as normally used for Minimum Phone Error (MPE) discriminative training, can be used instead as a decoding criterion for lattice rescoring. This is an alternative to Confusion Networks (CN) which are commonly used in speech recognition. The standard (Maximum A Posteriori) decoding approach is a Minimum Bayes Risk estimate with respe...

A method is presented for augmenting word n-gram counts in a matrix which represents a 2-gram Language Model (LM). This method is based on numerical distances in a reduced space obtained by Singular Value Decomposition (SVD). Rescoring word lattices in a spoken dialogue application using an LM containing augmented counts has lead to a Word Error Rate (WER) reduction of 6.5%. By further interpol...

Arabic has a large number of affixes that can modify a stem to form words. In automatic speech recognition (ASR) this leads to a high out-of-vocabulary (OOV) rate for typical lexicon size, and hence a potential increase in WER. This is even more pronounced for dialects of Arabic where additional affixes are often introduced and the available data is typically sparse. To address this problem we ...