How IntelliMetric Is Transforming Testing In Education

Education relies upon testing as a benchmark, and testing requires grading. In the past, this meant countless hours of work for human graders, manually reading each project or student essay for scoring. Today, IntelliMetric has changed that.

Since 1997, IntelliMetric has been the leading Artificial Intelligence software on the market for scoring constructed response work from students. It’s one of the most exciting applications of Natural Language Understanding (NLU) and AI since the technology’s inception.

As the first Artificial Intelligence platform to achieve essay scoring comparable with human scoring, IntelliMetric has since partnered with groups ranging from international organizations like the United Nations to academic bastions like the Graduate Management Admission Test (GMAT). 

Here are four fundamental ways that IntelliMetric is transforming testing in education.

Artificial Intelligence

First and foremost, IntelliMetric is built upon innovative Artificial Intelligence.

AI is “the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings. The term is frequently applied to the project of developing systems endowed with the intellectual processes characteristic of humans, such as the ability to reason, discover meaning, generalize, or learn from past experience.”1

You probably interact with AI in some form throughout your daily life. If you’ve ever asked Alexa, Google Home, Siri, or Cortana about the weather, then you’ve interacted with AI; if you’ve ever conducted an online search, that’s also AI; if you’ve ever played an online game against a computer, that’s AI, too.  Now you can use it to score all of the work your students produce.

Artificial Intelligence has rapidly progressed beyond incidental usefulness like home assistants and into advanced application creating efficiency in the research education sectors.

For instance, AI is thirty percent more accurate than humans at analyzing dark matter. By feeding simulated “dark matter maps” to the Artificial Intelligence, Alexandre Refregier’s research group trained a computer to work backward from light distortions and identify dark matter even more effectively than a human scientist.2

An Artificial Intelligence platform also benefits from an inherently blind approach to work that otherwise could be affected by bias. Dark matter may be strictly scientific—but when grading essay submissions written by people from multiple gender identities, racial/ethnic backgrounds, and more, an AI is better equipped than a human grader to discard presumption instead of demonstrating unconscious bias.

Danil Myakin, co-founder of Squilla Capital, explains, “Experts, like all people, are subject to cognitive distortions, which fundamentally affect the quality of the result. Prejudices, false assumptions, the desire to simplify, ignoring contradictions and, of course, the emotional component — all this affects the result, and all these weak points can be avoided with an introduction of AI in analytical processes. Moreover, experts’ opinions are too difficult to interpret unequivocally; they protect themselves and avoid specific details and clear phrases, which also exclude algorithms that produce dry numbers.”3

This bias-free application of AI is why IntelliMetric is trusted by international organizations like the United Nations, which hires personnel from all over the world; the Australian Council of Educational Research (ACER,) which assesses a vast number of online writing assessment submissions; and the sovereign wealth fund of Malaysia (Yayasan Kahzanah,) which filters thousands of scholarship applicants.

Automated Essay Scoring

IntelliMetric’s AI is the power behind its automated essay scoring. If allowing a computer to grade essays seems dubious at best, consider IntelliMetric’s decade-long partnership with the Graduate Management Admission Test (GMAT).

“The analytical writing assignment is scored by a human as well as a computer, and the two scores are averaged together,” applerouth.com explains. “By incorporating a computer into the grading process, the GMAT not only saves half the cost of grading the essay, but also is able to perform an objective analysis of sentence structure, word count, and complexity that a human reader would not have the time to complete. With a human reader assessing the coherence of the argument and the computer comparing the essay with its database of essays, the GMAT can enjoy the best of both worlds.”4

Natural Language

IntelliMetric relies upon a cutting-edge combination of Natural Language Processing (NLP) and Natural Language Understanding (NLU). The latter is technically a subset of the former. In short, NLU includes:

  • Relation extraction
  • Semantic parsing
  • Sentiment analysis
  • Question answering
  • Summarization

NLP also includes these features, but adds:

  • Named entity recognition
  • Part-of-speech tagging
  • Syntactic parsing
  • Text categorization
  • Co-reference resolution
  • Machine translation5

Both NLP and NLU work together to accomplish IntelliMetric’s high-level essay scoring. 

BMC explains: “Machines can find patterns in numbers and statistics, but understanding language takes a lot more: an understanding of a language’s syntax, the difference in how a language is spoken or written, pure context and definitions, shifting language patterns and ever-developing new definitions, picking up on subtleties like sarcasm which aren’t inherently readable from text, or understanding the true purpose or goal of a body of content. This is where NLP and NLU come in.”6

Through Natural Language Processing and machine learning, IntelliMetric does more than imitate a human grader—it works faster, more accurately, and without ever getting tired, providing thousands of unbiased essay scores in mere minutes.

From the United Nations to the Malaysian scholarship fund, IntelliMetric fuels accurate, fair essay assessment around the world and will only continue expanding in 2020. It’s more than Artificial Intelligence—it’s the next step for testing in education.

Additional Sources:

  1. https://www.britannica.com/technology/artificial-intelligence
  2. https://scitechdaily.com/artificial-intelligence-proves-30-more-accurate-than-humans-at-analyzing-dark-matter/ 
  3. https://hackernoon.com/artificial-intelligence-is-becoming-better-than-human-expertise-16903f4fc3c0
  4. https://www.applerouth.com/blog/2017/01/18/have-your-sat-essay-graded-by-a-computer/
  5. https://medium.com/sciforce/nlp-vs-nlu-from-understanding-a-language-to-its-processing-1bf1f62453c1 
  6. https://www.bmc.com/blogs/nlu-vs-nlp-natural-language-understanding-processing/ 
© 2024 Vantage Labs. All Rights Reserved.