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. 

app English International Certificate (PEIC)

app English International Certificate (PEIC) also uses automated assessment technology. With a two-hour test available on-demand to take at home or at school (or at a secure test center). Using a combination of advanced speech recognition and exam grading technology and the expertise of professional ELT exam markers worldwide, our patented software can measure English language ability.

Read more about the use of AI in our learning and testing here, or if you're wondering which English test is right for your students make sure to check out our post 'Which exam is right for my students?'.

Explore our courseware and exams

More blogs from app

  • Students sat outside on grass studying and smiling

    Building healthy New Year habits with your students

    By Amy Malloy
    Reading time: 3 minutes

    Balancing mindfulness and planning ahead

    Here we find ourselves already in a new year. I wonder if, like me, many of you might be wondering how that has happened. January is a time of year traditionally associated with analyzing the past and making resolutions for the future.

    In the classroom this might also involve looking forward to assessments and exams at the end of the school year. Maybe you’ve made New Year’s resolutions that have already fallen by the wayside.

    The focus of this blog is learning how to stay in the present moment. So let's take a practical look at how to manage this time of year with your students and with ourselves as teachers (and humans), while also effectively planning ahead for the future.

  • students sat at desks looking at their workbooks

    Mindfulness in the classroom: Autopilot and paying attention

    By Amy Malloy

    The challenge: the lure of automatic pilot

    Have you ever got to the bottom of the page in your favorite book and then realized you have no idea what you just read? This is due to being in a semi-conscious mental state called 'automatic pilot'. In automatic pilot mode, we are only partially aware of what we are doing and responding to in the present moment. If left to its own devices, it can end up masking all our thought patterns, emotions and interactions with those around us. Humans are habitual creatures, building functional 'speed-dials' to allow us to survive in the present while the mind is elsewhere planning for the future or ruminating in thought. The challenge here is that we are responding to the present moment based solely on habits learned from previous experience rather than making conscious choices based on the nuances of the moment itself. Luckily, mindfulness can help.

    The solution: the importance of paying attention on purpose

    Jon Kabat-Zinn, Professor Emeritus of Medicine at the University of Massachusetts Medical School, is often credited with bringing mindfulness into the secular mainstream. He defines the practice as: "paying attention in a particular way: on purpose, in the present moment and non-judgmentally."

    Paying attention on purpose is the skill needed to move out of automatic pilot. As such, practicing mindfulness starts with learning how to pay attention. The more we focus, the more the brain builds strength in the areas involved in this type of concentration - and the easier it becomes to do it automatically. In other words, it becomes a habit to be present.

    In the early years of primary school, a child's brain is developing more quickly than it ever will again. Young minds are in the process of forming their very first habits, and so learning to pay attention on purpose will have a .

    The why: why is this particularly important in schools?

    If you're a teacher wondering why this is important, mindfulness has many benefits in the classroom. Perhaps the most notable is its facility for improving children's attention span during English lessons and elsewhere in life. This is increasingly important as children are immersed in a world of digital screens and social media. Learning to focus can help to counteract the constant demands on their attention and develop greater patience and staying power for any one activity.

    , experts agree that our attention span varies depending on what we are doing. The more experience we have of how much attention a certain situation needs, the more the brain will adapt and make it easier for us to focus on those situations.

    The brains of school-age children develop rapidly. So, the more we can do to demonstrate to them what it feels like to pay attention for a prolonged period, the more likely they are to be able to produce that level of attention in similar situations.

    For teenagers it is even more important. During adolescence, our brains undergo a unique period of neural development. The brain rapidly streamlines our neural connections to make the brain function as efficiently as possible in adulthood. Like a tree shedding branches, it will get rid of any pathways that are not being used and strengthen up the areas that are being used: use it or lose it. So if teenagers are not actively using their ability to pay conscious attention and spending too much time in automatic pilot mode, through screen use and in periods of high exam stress, the brain won't just not strengthen their capacity to focus; it may make it harder for them to access the ability to pay attention in future.

    The how: three exercises to teach your students mindfulness

    These three mindfulness exercises will help your language students integrate awareness into everyday activities in their school and home lives.

    1. Mindful use of screens and technology

    Screen use is a major culprit of setting the brain into automatic pilot. This is an activity you canpractice in school during computer-based lessons or even ask the students to practise at home.

    • Close your eyes and notice how you feel before you've started
    • Consciously decide on one task you need to do on the device
    • Consciously think about the steps you need to do to achieve that task and visualize yourself doing them
    • Then turn on the device and complete the task. When you have finished, put the device down, walk away, or do something different
    • Notice if you wanted to carry on using the device (this doesn't mean we need to)

    2. Mindful snacking

    We eat so habitually that we rarely notice the huge range of sensory stimulation going onunder the surface of this process. This is a great activity to practise with your students during breaks or lunch.

    • Hold the snack in your hand and notice five things you can see about it
    • Close your eyes and notice five things about the way it feels in your hand or to touch
    • Keep the eyes closed and notice five things you can smell about the snack
    • Bring the snack slowly to your mouth and taste it – notice five different subtle tastes

    3. Counting the breath

    A brilliantly simple exercise to teach the brain to focus attention on one thing for a longerperiod of time. It can be done anywhere and can also have the helpful side effect ofreducing stress through passively slowing down the breath.

    • Close your eyes or take a soft gaze in front of you
    • Focus your attention on the breath going in and out at the nostrils
    • Notice the breath temperature on the way into the nose compared to its temperature on the way out
    • Count 10 breaths to yourself – in 1, out 1; in 2, out 2; and so on
    • If the mind wanders, gently guide it back to the breath
    • When you get to 10 you can either stop there or go back to 1 and start again
    • In time, it will become easier to stay focused for the full 10 breaths and for even longer

    If a part of you is still wondering where to start with mindfulness, then paying conscious attention to anything that draws our senses to the present moment: the breath, physical sensations in the body, sounds, smells or tastes - these are all brilliant places to start. Remember that mindfulness is simply a state of mind, a way of interacting with the world around us. How we access that state of mind can vary depending on the school, the language lesson and the students - there are many possibilities. As an English teacher, it's important to encourage and help students academically and in regards to their wellbeing.

  • A young girl meditating outside in a green space

    Does mindfulness really work? Can it help your students?

    By Amy Malloy

    What is mindfulness?

    The term mindfulness refers to a state of awareness. This is arrived at by paying conscious attention to the present moment and observing it without judgment, with curiosity and compassion.

    It is often confused with meditation, but really they’re not the same thing at all. Meditating and focusing on the breath is just one of the ways we can consciously pay attention and become more aware of ourselves and the present moment.

    You might be conscious that mindfulness has over the last decade. As with anything trendy, it can be easy to build preconceptions and dismiss it before trying it yourself. So let’s break it down together and start with the basics.

    Why is mindfulness important?

    Have you ever been driving somewhere in the car and noticed that you’ve arrived at your destination without really noticing the journey at all? All your thoughts on the way were elsewhere.

    This is called being on automatic pilot. It’s a symptom of our mind and body’s brilliant way of turning our everyday processes into a routine. It means we don’t need to think about it every time we need our body to move, speak or function.

    Just as the scenery can pass us by on a journey, so too can our thoughts and reactions to the things happening around us. They happen in our minds and bodies without us noticing. Our conscious mind is focused on something in the future, the past, or in our imaginations instead.

    Being on automatic pilot is often very helpful. But it also comes with a significant downside. Without us even realizing, negative thought cycles can build up under the surface. They can make us feel stressed and anxious.

    When this happens our minds conclude that there is a threat and sounds the alarm. This stress , ability to process new information, and ability to learn.

    This is where mindfulness comes in.

    Mindfulness helps us catch these in their tracks, allowing us to consciously notice negative thoughts. Rather than panicking, we become aware of how we are feeling – and why. We can therefore shift our relationship with our thoughts and emotions so that they don’t seem so challenging anymore.

    In a school setting, this can help students regulate the stress surrounding exam pressure. Students can also learn to sit more comfortably with the impermanent emotions of adolescence, which seemed all-consuming and everlasting at the time.

    What can our students learn from mindfulness?

    Over the past decade, neuroscientific research has discovered that our brains are immensely malleable. Every interaction we have in our day-to-day lives builds connections that affect how our brains and thoughts function. Just like building muscle through exercise, our brain forms new matter in the areas we use most.

    In short, we can either continue to cement the habits we’ve already formed or build brain matter in areas that encourage healthier, more positive functioning.

    Studies have demonstrated in many contexts that the brains of those who regularly practice mindfulness use different pathways to those who don’t: pathways which allow self-regulation of adrenaline and the stress responses and make it easier to experience external events without the accompanying narrative of critical thought.

    Even ten minutes of practicing mindful awareness a day has been . Mindfulness has also been shown to improve concentration and focus, resilience, emotional regulation and sleep quality in children, teens and adults alike.

    How can we begin to practice mindfulness?

    We start by learning to focus attention on a physical anchor. This may be focusing on the body, the breath, or even using the senses to observe sounds, sights, tastes, touch etc. in our external environment. We then build the length of time we can focus, and grow accustomed to the mind wandering and returning to the point of focus.

    Then we learn to be curious about what we notice in the present moment and that we can observe without judging or forming an opinion.

    In time, it can be possible to learn to observe our relationship with the thoughts that come in and out of our minds. We can then find ways to accept difficult feelings and allow them to pass over without panicking or instinctively reacting.

    Want to learn more about mindfulness and wellbeing? Check out our blog posts on the subject here.