Search

In machine translation (MT), one of the challenging tasks is to translate the proper nouns and technical terms from the source language to the target language while preserving the phonetic equivalent of original term. Machine transliteration, an essential part of MT systems, plays a vital role in handling proper nouns and technical terms. In this paper, a hybrid attention-based encoder–decoder machine transliteration system is proposed for the low-resource English to the Assamese language. In this work, the proposed machine transliteration system is integrated with the previously published hybrid attention-based encoder–decoder neural MT model to improve the translation quality of English to the Assamese language. The proposed integrated MT system demonstrated good results across various performance metrics such as BLEU, sacreBLEU, METEOR, chrF, RIBES, and TER for English to Assamese translation. Additionally, human evaluation was also conducted to assess translation quality. The proposed integrated MT system was compared with two existing systems: the Bing translation service model and the Samanantar Indic translation model.

Introduction:

Disasters are high-acuity, low-frequency events which require medical providers to respond in often chaotic settings. Due to this infrequency, skills can atrophy, so providers must train and drill to maintain them. Historically, drilling for disaster response has been costly, and thus infrequent. Virtual Reality Environments (VREs) have been demonstrated to be acceptable to trainees, and useful for training Disaster Medicine skills. The improved cost of virtual reality training can allow for increased frequency of simulation and training.

Problem:

The problem addressed was to create a novel Disaster Medicine VRE for training and drilling.

Methods:

A VRE was created using SecondLife (Linden Lab; San Francisco, California USA) and adapted for use in Disaster Medicine training and drilling. It is easily accessible for the end-users (trainees), and is adaptable for multiple scenario types due to the presence of varying architecture and objects. Victim models were created which can be role played by educators, or can be virtual dummies, and can be adapted for wide ranging scenarios. Finally, a unique physiologic simulator was created which allows for dummies to mimic disease processes, wounds, and treatment outcomes.

Results:

The VRE was created and has been used extensively in an academic setting to train medical students, as well as to train and drill disaster responders.

Conclusions:

This manuscript presents a new VRE for the training and drilling of Disaster Medicine scenarios in an immersive, interactive experience for trainees.

Search Results

Refine search

Refine search

Actions for selected content:

2 results

Improving neural machine translation by integrating transliteration for low-resource English–Assamese language

Creating a Novel Disaster Medicine Virtual Reality Training Environment

Search Results

Refine search

Refine search

Actions for selected content:

Save Search

2 results

Improving neural machine translation by integrating transliteration for low-resource English–Assamese language

Creating a Novel Disaster Medicine Virtual Reality Training Environment