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. 

Read more about the use of AI in our learning and testing here.

Explore our courseware and exams

More blogs from app

  • A child and parent laying on a carpet staring at eachother and smiling

    Mindfulness activities for kids to reduce stress

    By Amy Malloy

    How can we help children (and ourselves) deal with turbulent situations?

    As humans, we are programmed to position ourselves according to the constants around us: people, structures and boundaries. When those constants shift, it can be unsettling for adults and children.

    Sometimes we find ourselves in unprecedented situations, and we each have our own approach to managing things. If you feel confused and without direction because of a turbulent situation, please know that that is okay.

    We’ll look today at why that is, to help us understand ourselves a little more and why these simple mindfulness activities can help us navigate it.

    What causes social stress?

    There may be many reasons for feeling stressed in life, but during turbulent times in society, it is often due to not feeling safe.

    Something in our environment is alerting our survival instinct. This makes our brains produce stress hormones, which get us ready to fight the threat, run from it, or freeze until it’s gone away.

    The threat might be to our physical or even social survival – and the two are linked. Things can feel even scarier when we also feel isolated from our social group, which keeps us protected from that threat.

    Human beings are social by nature. We live and work in communities, we connect through love and empathy and we protect each other. There’s truth to the saying“there’s safety in numbers”.

    But it’s not just about safety. We also define ourselves by comparing ourselves to others and working out what we are not.

    Research has found that we identify deeply with our role in society and the ‘pack’ to which we belong. This holds deep ties with our sense of safety, contentment and self-esteem. If the boundaries by which we define and position ourselves have shifted or continue to shift, we will feel unsafe, threatened and therefore stressed.

    Are children affected by social stress in the same way?

    If we then apply this to children, the constants to whom they look for security are the adults in their life. If the adults are behaving differently, the children will feel a shift and feel unsafe and stressed too. If they don’t have their friends alongside them for social positioning, this too can lead to them feeling confused and uncertain.

    Here are some key ways we can help:

    Communicating and listening

    Children may often lack the language to express what they are feeling, or even to recognize it themselves. Therefore, we must offer ways to help them make sense of the world around them, to help them feel safe and to help express their concerns.

    Communication provides the necessary social interaction and models for them on how to handle the new situation. It firms up their boundaries, and provides a safe space where they feel listened to and acknowledged and this, in turn, helps diffuse their stress.

    The activity below is a lovely way to invite children to express any worry they might be feeling, mindfully and with support – and give them something to do with their feelings. It also has the benefit of helping them breathe fully and slowly, which will calm down their nervous system.

    Breath activity: Worry bubbles

    1. Sit together and invite your child to put their palms together.
    2. Invite them to take a big breath in. As they breathe in, they can draw their palms further and further apart, spreading their fingers as they imagine blowing up a big bubble between their hands.
    3. Invite them to whisper a worry into the bubble.
    4. Invite them to blow the breath out nice and slowly. As they breathe out, they can imagine blowing the bubble (and the worry) away with a big sigh.
    5. Twinkle the fingers back down to the lap, and start again, either with the same worry or a new one

    Helping them find a safety anchor inside themselves

    By helping children focus on breathing, we can teach them that even if things feel wobbly around them, their breath is always there. The act of focusing on the breath also helps settle the fight or flight branch of their nervous system into a calmer, more balanced state.

    Breath Activity: Counting breaths

    1. Invite your child to sit with you.
    2. Invite them to place their hands on their tummy and breathe in slowly so they push into their hands, counting slowly up to four.
    3. As they breathe out, invite them to count up to six, as they slowly empty the belly and their hands lower back down.
    4. Continue until they feel calmer. You can do this every morning or evening to help sustain balance. With younger children, they might like a teddy on their tummy to push up and down!

    These two activities can be lovely daily practices to try and provide some safety and structure to your child or students’ mental health right now. They are also enjoyable activities to try for yourself – you may like to increase the in and out count of the breath a little bit for an adult breath.