Can computers really mark exams? Benefits of ELT automated assessments

app Languages
Hands typing at a laptop with symbols

Automated assessment, including the use of Artificial Intelligence (AI), is one of the latest education tech solutions. It speeds up exam marking times, removes human biases, and is as accurate and at least as reliable as human examiners. As innovations go, this one is a real game-changer for teachers and students. 

However, it has understandably been met with many questions and sometimes skepticism in the ELT community – can computers really mark speaking and writing exams accurately? 

The answer is a resounding yes. Students from all parts of the world already take AI-graded tests.  aԻ Versanttests – for example – provide unbiased, fair and fast automated scoring for speaking and writing exams – irrespective of where the test takers live, or what their accent or gender is. 

This article will explain the main processes involved in AI automated scoring and make the point that AI technologies are built on the foundations of consistent expert human judgments. So, let’s clear up the confusion around automated scoring and AI and look into how it can help teachers and students alike. 

AI versus traditional automated scoring

First of all, let’s distinguish between traditional automated scoring and AI. When we talk about automated scoring, generally, we mean scoring items that are either multiple-choice or cloze items. You may have to reorder sentences, choose from a drop-down list, insert a missing word- that sort of thing. These question types are designed to test particular skills and automated scoring ensures that they can be marked quickly and accurately every time.

While automatically scored items like these can be used to assess receptive skills such as listening and reading comprehension, they cannot mark the productive skills of writing and speaking. Every student's response in writing and speaking items will be different, so how can computers mark them?

This is where AI comes in. 

We hear a lot about how AI is increasingly being used in areas where there is a need to deal with large amounts of unstructured data, effectively and 100% accurately – like in medical diagnostics, for example. In language testing, AI uses specialized computer software to grade written and oral tests. 

How AI is used to score speaking exams

The first step is to build an acoustic model for each language that can recognize speech and convert it into waveforms and text. While this technology used to be very unusual, most of our smartphones can do this now. 

These acoustic models are then trained to score every single prompt or item on a test. We do this by using human expert raters to score the items first, using double marking. They score hundreds of oral responses for each item, and these ‘Standards’ are then used to train the engine. 

Next, we validate the trained engine by feeding in many more human-marked items, and check that the machine scores are very highly correlated to the human scores. If this doesn’t happen for any item, we remove it, as it must match the standard set by human markers. We expect a correlation of between .95-.99. That means that tests will be marked between 95-99% exactly the same as human-marked samples. 

This is incredibly high compared to the reliability of human-marked speaking tests. In essence, we use a group of highly expert human raters to train the AI engine, and then their standard is replicated time after time.  

How AI is used to score writing exams

Our AI writing scoring uses a technology called . LSA is a natural language processing technique that can analyze and score writing, based on the meaning behind words – and not just their superficial characteristics. 

Similarly to our speech recognition acoustic models, we first establish a language-specific text recognition model. We feed a large amount of text into the system, and LSA uses artificial intelligence to learn the patterns of how words relate to each other and are used in, for example, the English language. 

Once the language model has been established, we train the engine to score every written item on a test. As in speaking items, we do this by using human expert raters to score the items first, using double marking. They score many hundreds of written responses for each item, and these ‘Standards’ are then used to train the engine. We then validate the trained engine by feeding in many more human-marked items, and check that the machine scores are very highly correlated to the human scores. 

The benchmark is always the expert human scores. If our AI system doesn’t closely match the scores given by human markers, we remove the item, as it is essential to match the standard set by human markers.

AI’s ability to mark multiple traits 

One of the challenges human markers face in scoring speaking and written items is assessing many traits on a single item. For example, when assessing and scoring speaking, they may need to give separate scores for content, fluency and pronunciation. 

In written responses, markers may need to score a piece of writing for vocabulary, style and grammar. Effectively, they may need to mark every single item at least three times, maybe more. However, once we have trained the AI systems on every trait score in speaking and writing, they can then mark items on any number of traits instantaneously – and without error. 

AI’s lack of bias

A fundamental premise for any test is that no advantage or disadvantage should be given to any candidate. In other words, there should be no positive or negative bias. This can be very difficult to achieve in human-marked speaking and written assessments. In fact, candidates often feel they may have received a different score if someone else had heard them or read their work.

Our AI systems eradicate the issue of bias. This is done by ensuring our speaking and writing AI systems are trained on an extensive range of human accents and writing types. 

We don’t want perfect native-speaking accents or writing styles to train our engines. We use representative non-native samples from across the world. When we initially set up our AI systems for speaking and writing scoring, we trialed our items and trained our engines using millions of student responses. We continue to do this now as new items are developed.

The benefits of AI automated assessment

There is nothing wrong with hand-marking homework tests and exams. In fact, it is essential for teachers to get to know their students and provide personal feedback and advice. However, manually correcting hundreds of tests, daily or weekly, can be repetitive, time-consuming, not always reliable and takes time away from working alongside students in the classroom. The use of AI in formative and summative assessments can increase assessed practice time for students and reduce the marking load for teachers.

Language learning takes time, lots of time to progress to high levels of proficiency. The blended use of AI can:

  • address the increasing importance of formative assessmentto drive personalized learning and diagnostic assessment feedback 

  • allow students to practice and get instant feedback inside and outside of allocated teaching time

  • address the issue of teacher workload

  • create a virtuous combination between humans and machines, taking advantage of what humans do best and what machines do best. 

  • provide fair, fast and unbiased summative assessment scores in high-stakes testing.

We hope this article has answered a few burning questions about how AI is used to assess speaking and writing in our language tests. An interesting quote from Fei-Fei Li, Chief scientist at Google and Stanford Professor describes AI like this:

“I often tell my students not to be misled by the name ‘artificial intelligence’ — there is nothing artificial about it; A.I. is made by humans, intended to behave [like] humans and, ultimately, to impact human lives and human society.”

AI in formative and summative assessments will never replace the role of teachers. AI will support teachers, provide endless opportunities for students to improve, and provide a solution to slow, unreliable and often unfair high-stakes assessments.

Examples of AI assessments in ELT

At app, we have developed a range of assessments using AI technology.

Versant

The Versant tests are a great tool to help establish language proficiency benchmarks in any school, organization or business. They are specifically designed for placement tests to determine the appropriate level for the learner.

PTE Academic

The  is aimed at those who need to prove their level of English for a university place, a job or a visa. It uses AI to score tests and results are available within five days. 

More blogs from app

  • A group of business people stood around a board with sticky notes on smiling

    Craft the perfect job description: Ensure your candidates have the right English proficiency

    By Samantha Ball
    Reading time: 3 minutes

    English is the international language of business and a foundational skill for many roles. The right level of English proficiency is key for individuals and businesses to excel.

    But what is the “right” level?

    English is not a one-size-fits-all skill. Customer Service Representatives need different English skills to IT Systems Managers. Senior staff will often need more advanced English skills than junior staff.

  • A group of students sat together in a library around a laptop smiling

    Forgetting to remember – What active recall is all about

    By Heath Pulliam
    Reading time: 5 minutes

    Heath Pulliam is an independent education writer with a focus on the language learning space. He’s taught English in South Korea and various subjects in the United States to a variety of ages. He’s also a language learning enthusiast and studies Spanish in his free time.

    Almost everyone has studied for a test at some point in their life. Have you ever studied a lot for a test and still not received a great grade? Probably so. This is because not all study methods are created equal. Just because you’ve ‘studied’ doesn’t necessarily mean that the material has stuck in your brain.

    Some common study methods don’t do as much as you might think. One technique, however, stands out for its efficiency and effectiveness. It’s called active recall, and it’s regarded by many as the best way to study.

    What is active recall?

    In short, active recall is the process of pulling information from your brain without prompts. The idea is that when you force yourself to remember something, you memorize it much faster than you would by only reading material or passively studying.

    When you’re taking a test and you’re not sure about an answer, you search your brain for the answer; that’s active recall. The action of trying to remember is what essentially crystallizes the information in your head for the long term. Multiple study methods use active recall or the action of searching your brain for an answer.

    Active recall forces you to pull information from your mind. It’s not just for doing well on tests but also for long-term retention.

    Active recall is praised for its effectiveness, but it is also mentally taxing. Attempting to recall things that are not in the front of your mind is tiring, which is part of why some opt out of using it.

    Dr. Cal Newport, author of Deep Work, says:

    “It’s almost like you have a pseudo-photographic memory when you study this way.”

    Passive and active study

    Most people are taught to study, but less about how to study. People end up using passive study techniques, like rereading material or rewatching lectures. Although not particularly effective, studies show that reading and rereading notes remains university students’ most common study method. (Dunlosky, 2013).

    These methods might feel like effective studying but aren’t really helping much. Yes, passive study methods such as reading, highlighting, or watching can help, but can also give you a false sense of understanding.

    With these methods, when the time comes to retrieve the information, you struggle to recall it because it is not in your long-term memory.

    The first step to becoming excellent at studying is understanding how important active study methods are, such as flashcards, practice testing, or practice teaching – all methods that use active recall.

    Spaced repetition

    If you’re researching study methods, you’ve probably encountered the term spaced repetition. This technique can be incorporated into active recall study methods, primarily flashcards.

    Spaced repetition involves reviewing information at increasingly longer intervals in order to improve long-term memory. You are using this technique when you learn something, so review it a day later, then a week later and then a month later. It helps fight your brain’s natural process of forgetting things.

    Combining spaced repetition with active recall is always a recipe for successful study.

    So, what methods can you use to employ active recall in your study sessions?

    Summarize what you know

    The simplest way to practice active recall is to try to remember the material actively. To do this, read or reread some material, then take some time away—take a walk, snack break, or whatever you like to do to take a break.

    During this break, try to replicate in your mind as much about the topic from scratch as if you had to teach about it. Don’t be discouraged if you have trouble remembering; part of the learning process is forgetting material and then remembering it.

    When using this for language acquisition, make up relevant sentences and translate them into your target language. What type of vocabulary were you learning? What grammatical structures were new to you?

    Take a mental note of which elements you were able to remember and which ones gave you trouble.

    When finished, go back to the material and review. Were you able to remember things? Whether you could or not, you’ve helped yourself. Your attempt to remember is you practicing active recall.

    When you do successfully remember something, you’ll realize that it is locked in your long-term memory. This method is as simple as it is productive.

    Teach a friend

    Similar to mental summarizing, after studying, find a friend and do your best to explain the topic to them. Language learning could involve explaining how a new grammar pattern works in your target language or taking sentences and phrases and translating them to a friend.

    As a teacher, your best lessons are the ones where you know the material inside and out. If you can effectively explain and teach someone about your target language, you are that much closer to mastering the information yourself.

    Flashcards

    Flashcards, especially when combined with spaced repetition, are the king of study methods for language acquisition.

    Between all that they can be used for, they are especially good for language learning, no matter what part of the language you’re studying. This is one of the best ways to learn sentence structure that does not mirror your native tongue, conjugations for speedy use and general vocabulary.

    I have found that using a spaced repetition-based flashcard program is the best way to study a language. This way, you don’t have to schedule a bunch of paper flashcards manually.

    Among the most popular programs for language learners is Anki. Anki is a spaced repetition flashcard program. With it, you create your cards and the program schedules them at increasingly longer intervals. It is also used widely among students studying for large tests, like medical and law exams.

    To make the best flashcards, make them yourself. Downloading a big set of flashcards for your target language is tempting but not particularly helpful. Instead, after each study session, make a few flashcards yourself covering the new vocabulary/grammar you’ve just learned about.

    One more thing: do not use multiple-choice answers for your cards. Active recall happens when you produce information without prompts or assistance.

    Personally, I use flashcards every day to learn Spanish through . This program has a learning curve, but the payoff makes it worth it.

    Test yourself

    The goal of studying for a test is to be able to answer questions about a topic or, even better, know the material for real-world application. As stated earlier, active recall happens during testing, so why not use this form of active recall before testing?

    Use your materials to make a mock exam in this method, then take it. Through actively remembering to answer each question, the ones you get right will stick in your brain. Review the questions that you couldn’t remember and retake the test focusing on them.

    While not particularly complicated, these tips and methods’ effectiveness comes from their use of active recall. As you forget information and pull it from the depths of your memory, you solidify it for yourself.

    Forgetting plays an important role in learning something for long-term memory.

    Now, get to studying; how are you going to use the power of active recall in your routine?

    References

    Dunlosky, J. "Improving Students’ Learning With Effective Learning Techniques: Promising Directions From Cognitive and Educational Psychology." Association for Psychological Science, 2013, 1-6

  • placeholder

    Understanding your GSE score

    By Samantha Ball
    Reading time: 3 minutes

    For many students, navigating the world of English language proficiency tests can be a daunting experience. Whether you're preparing for university, looking to enhance your career prospects, or simply aiming to improve your communication skills, understanding what your Global Scale of English (GSE) score means is crucial.

    In this blog post, we'll break down the GSE, explain what your score represents and provide you with actionable steps to improve it.