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 couple sat on a sofa one with a laptop the other with a book; they are both laughing

    How English conversation works

    By Richard Cleeve

    English language teachers everywhere spend time and energy helping students practice their conversation skills. Some may ask whether conversation in English can actually be taught. And – if it can – what the rules might be.

    To explore these questions, we spoke to world-renowned . He is an Honorary Professor of Linguistics at the University of Bangor and has written more than 120 books on the subject.

    What makes a good conversation?

    “It’s very important that we put this everyday use of language under the microscope,” he says. He highlights three critical facets of conservation that we should bring into focus:

    • Fluency
    • Intelligibility
    • Appropriateness

    But all in all, he says that people should walk away from a conversation feeling like they’ve had a good chat.

    “For the most part, people want that kind of mutual respect, mutual opportunity, and have some sort of shared topic about which they feel comfortable – and these are the basics I think.”

    The rules of conversation

    There are plenty of ways you can teach learners to engage in a successful conversation – including how to speak informally, use intonation, and provide feedback. So let’s take a look at some of the key areas to focus on:

    1) Appropriateness

    Fluency and intelligibility are commonly covered in English language classes. But appropriateness can be more complicated to teach. When preparing to teach conversational appropriateness, we can look at it through two different lenses: subject matter and style:

    2) Subject matter

    “What subject matter is appropriate to use to get a conversation off the ground? There are cultural differences here,” he says. The weather is often a good icebreaker, since everyone is affected by it. The key is to find a common topic that all participants can understand and engage with.

    3) Style

    Teachers can also teach students about conversational style, focusing on how to make conversations more relaxed in English.

    There are “several areas of vocabulary and grammar – and pronunciation too, intonation for example – as well as body language, in which the informality of a conversation is expressed through quite traditional means,” says David. One example he offers is teaching students how to use contracted verb forms.

    4) Simultaneous feedback

    This is what makes a conversation tick. When we talk with someone, we let them know we’re listening by giving them feedback. We say things like “really” or “huh” and use body language like facial expressions and gestures.

    Of course, these feedback noises and expressions can be taught. But they won’t necessarily be new to students. English learners do the same when speaking their own language, anyway.

    Keep in mind though, that when it comes to speaking online on video conferencing platforms, it’s not easy to give this type of simultaneous feedback. People’s microphones might be on mute or there might be a delay, which makes reacting in conversations awkward. So, says David, this means online conversations become much more like monologues.

    5) Uptalk and accents

    Uptalk is when a person declares something in a sentence, but raises their intonation at the end. For English learners, it might sound like someone is asking a question.

    Here’s an example:

    • “I live in Holyhead” said in a flat tone – this is a statement.
    • “I live in Holyhead” said using uptalk – you are stating you live here, but recognize that someone else might not know where it is.

    Now, should teachers teach uptalk? David says yes. For one, it’s fashionable to speak this way – and it can be confusing for English learners if they don’t understand why it’s being used in a conversation.

    “The other thing is that we are dealing here with a genuine change in the language. One of the biggest problems for all language teachers is to keep up to date with language changes. And language change can be very fast and is at the moment,” he says.

    When it comes to accents, David is a fan. “It’s like being in a garden of flowers. Enjoy all the linguistic flowers,” he says, “That’s the beauty of language, its diversity”.