Natural lANGUAGE

DVA's become more powerful when they communicate with natural language. Google Assistants, Alexa, and Siri apply natural language to make the systematic interaction with the users more personalized. The recall and responses get smarter and more predictive. If the systems are getting smarter, the better tutor they come in education. They can answer questions and guide the students more effectively. DVA's like Alexa has AI and Natural Language to achieve the level of interactions required for instruction assistance. VA's with AI will do the tricks, but natural language boost the successful output for the student, as well as expanding the scope of tasks it can automate for the isntructors.

One example of how natural language can help Virtual Assistants is from an article named "Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics". The article is good to read on ways to show the opportunities of natural languge.

The mechanisms can take visual and language observations and translate into computer learning (Wiriyathammabhum, Summers-Stay, Fermuller, and Aloimonos, 2016). Recognition, reorganization, and reconstruction is a model for how computers manage visual and language information. Computers make a 3D model and uses information to learn and use for later. When the computer reconstructs the information there is improved grouping models for later recall.

Spoken language technology is important to digital virtual assistants. The communication back to the customer is continually. These technologies are part of assistants like Siri, Alexa, and Google Assistant. Dialog scenarios are communications mapped out and set up with voice context. Instructional designers can map out dialog scenarios. Most systems map to online content stored in the cloud. The idea is to use wider knowledgebases of user-generated content. Templates can be modified for specific content and system can seach the vast databases on the web (Nishimura, Yamamoto, Uchiya, and Takumi, 2018).

Dynamic semantic models managing the natural language can be added to build cognitive leearning. The natural language interactions become more intentional, which also evolves the conversation to be symetric, matching the intent of human (Bernard and Arnold, 2019). Adding natural language to virtual assistants with other layers of components provide the best opportunity to build effective assistants in learning. The DVA's enhance and add the compentence level that can make students more comfortable with the systems. The DVA then becomes the tutor, a guide, grades the papers, or providing assistance with questions and tasks. DVA's are the future. The time is now to embrace the magic and get them injected into more of our instructional models.