Can computers really mark exams? Benefits of ELT automated assessments

ɫèAV 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.  and 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 ɫèAV, we have developed a range of assessments using AI technology, including , 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 ɫèAV

  • Two friends outside laughing together

    Exploring unusual and funny English sayings

    By Charlotte Guest
    Reading time: 3 minutes

    It's April Fool's Day today and we’re diving into the lighter side of the English language. English is full of quirky sayings and odd words that can leave you scratching your head or laughing out loud. So enjoy this collection of funny English sayings and words that are sure to bring a smile to your face and probably make you question whether this is an April Fool’s Day joke.

    1. Bob’s your uncle

    Let’s start with a classic British saying: “Bob’s your uncle.” This phrase is used to indicate that something will be simple or straightforward. For example, “Just add water, and Bob’s your uncle”. But who is Bob, and why is he your uncle? The origins are unclear, but it’s a fun way to say, “And there you have it”.

    2. The bee’s knees

    When something is the “bee’s knees,” it means it’s excellent or of high quality. But why the knees of a bee? This saying likely originated in the 1920s as part of a trend of using animal anatomy in slang. Other similar phrases include “the cat’s pajamas” and “the snake’s hips”.

    3. More holes than Swiss cheese

    If something has “more holes than Swiss cheese,” it means it’s full of flaws or problems. This saying is self-explanatory if you’ve ever seen a slice of Swiss cheese. It’s a humorous way to point out that something isn’t quite up to par.

    4. Bamboozle

    To “bamboozle” someone means to trick or confuse them. This word itself sounds like a bit of a trick, doesn’t it? It’s believed to have originated in the 17th century, and it’s a perfect word to use on April Fool's Day when you’re pulling pranks on your friends.

    5. Fuddy-duddy

    A “fuddy-duddy” is someone who is old-fashioned or fussy. This term is often used affectionately to describe someone who is a bit behind the times. It’s a funny-sounding word that’s sure to bring a smile to your face.

    6. Gobbledygook

    “Gobbledygook” refers to language that is meaningless or hard to understand, often used to describe overly complex jargon. It was coined during World War II by a Texas congressman who compared confusing bureaucratic language to the sound of a turkey’s gobble. It’s a perfect word for describing those moments when someone is talking but you have no idea what they’re saying.

    7. Mad as a hatter

    If someone is “mad as a hatter,” they’re completely crazy. This saying dates back to the 19th century when hat makers (hatters) often suffered from mercury poisoning due to the chemicals used in hat production, leading to erratic behavior. It’s a whimsical way to describe someone who’s a bit off their rocker.

    8. Raining cats and dogs

    When it’s “raining cats and dogs”, it’s raining very heavily. The origins of this saying are unclear, but it’s a vivid and amusing way to describe a downpour. Just imagine cats and dogs falling from the sky!

    9. Lollygag

    To “lollygag” means to dawdle or waste time. It’s a playful word that perfectly captures the essence of goofing off. So, if you find yourself procrastinating today, just tell everyone you’re lollygagging.

    10. The whole shebang

    “The whole shebang” means everything or the entire thing. The origins of “shebang” are uncertain, but it’s a fun and quirky way to refer to the entirety of something. Whether you’re talking about a project, a meal or a party, this phrase adds a bit of flair.

    11. Cat got your tongue?

    When someone is unusually quiet or at a loss for words, you might ask “Cat got your tongue?” This odd saying dates back to the 19th century and is a humorous way to prompt someone to speak up.

    12. As cool as a cucumber

    If someone is “as cool as a cucumber,” they’re very calm and composed, even in stressful situations. This saying is amusing because it compares a person’s demeanor to a vegetable known for its refreshing coolness. It’s a fun way to compliment someone’s ability to stay unruffled.

    How many unusual English sayings do you know?

    English is a wonderfully weird language, full of sayings and words that can leave us amused and bewildered. On this April Fool's Day, we hope you’ve enjoyed this lighthearted look at some of the funniest expressions English has to offer. So go ahead, sprinkle these sayings into your conversations, and share a laugh with your friends. After all, laughter is the best medicine, and today is the perfect day to embrace the humor in our language.

  • A teacher stood next to a young students desk, the student sat at the desk is high fiving his teacher

    What is the ɫèAV Smart Lesson Generator?

    By Thomas Gardner
    Reading time: 3 minutes

    How much of your valuable time is spent on planning and administrative tasks instead of teaching? While 93% of educators start their careers to positively impact students' lives, over 75% end up overwhelmed by these non-teaching duties. But we have a tool to help lighten the load.

    Introducing ɫèAV Smart Lesson Generator– a fast, integrated and efficient solution to streamline lesson planning, allowing you to focus on teaching. Let’s explore the Smart Lesson Generator:

    Meet the new ɫèAV Smart Lesson Generator

    The ɫèAV Smart Lesson Generator allows you to create engaging and appropriate lesson plans in seconds. It is connected with ɫèAV courses designed by experts and aligned with the Global Scale of English (GSE) to ensure effectiveness.

  • A group of students hugging a teacher

    How to use praise to motivate your students

    By Joanna Wiseman
    Reading time: 3 minutes

    Praise in the classroom is a valuable resource that every teacher has in their toolbox.It can encourage struggling students and reward learners who have been studying diligently and working hard on their language skills.

    But not all types of praise have the same effect. Let’s take a look at different types of praise and how you can use it to boost your learners’ motivation andself-esteem.

    Different types of praise in the classroom

    There are three types of praise that teachers commonly engage in - but they’re not all equal and are not all desirable:

    • Personal praise: Here you praise a student for a specific ability or quality. For example, you might say something like,“You have a great memory for vocabulary”.
    • Effort-based praise: Thisis when you comment on a student’s efforts. For example, you could say,“I can see you tried really hard with this vocabulary homework – well done.”
    • Behavior-based praise:This type of praiseis where you comment on how a student is acting, an example would be,“You were really paying attention during the vocabulary lesson – good job.”

    So how – and when – should we use these types of praise in the classroom?

    Try not to praise ability

    The first type of praise – personal praise – should be avoided in the classroom.has shown that this type of praise doesn’t have a beneficial effect on motivation.

    In fact, praise for intelligence actually has a detrimental effect on student achievement. When students were praised for their intelligence, they tended to care more about their performance goals – the score they achieved on a test, for example. Learning goals, like mastering a new skill, became less important to them.

    Moreover, personal praise has been shown to undermine student resilience in the face of failure. Students showed less persistence when it came to challenging tasks and less enjoyment of the challenge. They also performed more poorly than children praised for effort.

    Furthermore, when you praise students for their ability, they also tend to see intelligence or aptitude as a fixed trait. However, students who are praised for effort are more likely to see ability as something they can improve on. This feeds into the development of a growth mindset vs a fixed mindset.It’s important toinstilla growth mindset in learners to enable them to reach their full potential.

    How to praise effort and behavior

    When it comes to praising effort and behavior, what’s the most effective way to do it? Here are some techniques to employ:

    1. Be specific

    General praise such as “Good job” isn’t nearly as effective as a comment that shows you’ve been paying attention to what the student is doing. A precise compliment will make a much bigger impact on a student, for example:“I was really impressed at how hard you concentrated during the listening exercise. Well done.”

    2. Give praise in the moment

    Immediate praise doesn’t need to be disruptive, but it shows students that you are paying attention and noticing good behavior and effort.

    3. Avoid comparisons with other students

    Instead of saying, “You got the best mark in the class – well done!” say something like,“You got a really high score in the reading test. Your hard work has really paid off this term.”

    4. Keep track of praise

    Before your class, choose three or four students you’re going to praise that day. That way, you can be sure that each and every student will benefit from the motivational power of effective classroom praise!

    5. Personalize your praise, depending on the student

    Young students enjoy being praised publicly, but shy students, older children and teenagers prefer positive feedback to be given quietly.

    Don’t overpraise and watch your positive bias

    It’s important to be sincere. Older children, especially adolescents, have an extremely low tolerance of insincerity. So, don’t be tempted to praise students too often, or too effusively – it can actually have a negative impact on your relationship with your whole class. Insincere praise can lead students to question your judgement.

    It’s also really important to be aware of your positive bias.that teachers consistently give students of color more positive feedback on their work. It’s done with good intentions, but it can actually be harmful. If you regularly overpraise students for minor achievements, it can imply that you have low expectations for these students. And, this can make your students feel like they might not be capable of fulfilling the high expectations that you should have of them.

    So, instead of overpraising, focus on giving specific, immediate praise to motivate your students, boost theirself-esteem and unlock their potential.