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

  • A teacher sat at a table with students helping them work

    GSE Teacher Toolkit: Teaching mixed ability classes

    By Sara Davila
    Reading time: 4 minutes

    One of the biggest challenges for language teachers is teaching a mixed ability class. Students with different levels and abilities will always be present in our classrooms. So, how can we use the to improve mixed ability teaching? Let’s find out.

    How to teach mixed-ability classes

    Differentiated instruction is the best way to address the challenges of mixed ability classrooms. This is a method that helps teachers adjust aspects of the curriculum to match the different levels ofstudents.*This practice ensures that all learners are meeting course outcomes, even though their learning experience may be varied anddifferent.

    In order to differentiate instruction and support students with different needs, teachers can change:

    • the content being taught
    • the process used to teach
    • the product students create
    • the environment where learning takes place

    Adjusting the content tends to be the most obvious way to support learners. So, teachers who want to engage with differentiated instruction in mixed ability classrooms often find themselves producing a lot of content. This is greatas a way tosupport learners. However, creating new content or leveling existing content is time-consuming, and it can become a real challenge for teachers.

    Content vs process

    Instead of adjusting your content, you can use the GSE Teacher Toolkit to adjust your process. When you’re not creating lots of new content, you’ve got more time to consider how to teach new language to your students and how they can show what they’ve learned.The GSE Teacher Toolkit helps teachers to focus on the process and language production of learners, rather than the content you are teaching.

    This means less work for you, and more engagement from your students, no matter what their level is. And the GSE Teacher Toolkit can help you understand the skills we can expect students to demonstrate. So how does this work in practice? Let’stake a look.

  • Students sat at a desk looking at a textbook together, with a teacher pointing to it

    Real-world English: How GSE Job Profiles bridge learning and work

    By Sara Davila
    Reading time: 5 minutes

    Did you know that improving your English proficiency can increase earning potential by up to 50% and safeguard your career against AI? Recent research by ɫèAV highlights that English is not just a skill but a career-defining advantage in today’s globalized workplace. For millions of adult learners, the journey from the classroom to the workplace requires more than general conversational abilities—it’s about gaining targeted, job-ready skills as quickly as possible. For English language educators, understanding what “jDz-𲹻” English is and how to identify “jDz-𲹻” skills can provide a significant advantage in ensuring learners are prepared to communicate effectively and collaborate with their future coworkers.

    That’s where the Global Scale of English (GSE) Job Profiles comes in. For educators and program developers, it offers a bridge between real-world job skills and the English learners need to perform them. Whether you’re creating programs for nursing assistants, hospitality workers, or IT professionals, this tool ensures that learners build the precise English skills they need to thrive in their roles.

    Let’s walk through how to create a GSE Job Profile and explore its practical use for building programs that align with today’s professional realities.

  • Children sat at desks at computers in a classroom

    21st-century skills and the English language classroom

    By Sara Davila

    Are you teaching in a 21st-century classroom? Chances are, If you are an English educator working in the classroom today, you have already moved well ahead of your peers and colleagues teaching math, science, and good old-fashioned grammar. Now that you know you are a 21st-century teacher, what does that mean? And how do you know if you have moved ahead of the curve to embrace what we call 21st-century skills?

    Actually, "21st-century skills" is a bit of a misnomer. The prized skills of this age have existed in teaching and learning as long as we have been teaching and learning. In a modern-day class, Socrates and Aristotle would feel right at home (although maybe underdressed).

    The phrase itself is meant to imply a classroom ready for the upcoming STEM needs of employment that will allow for innovation, development and significant advances across tech and non-tech industries. Yet, the skills themselves do not imply a highly technological classroom. A modern 21st-century class can be a surprisingly low-budget place.

    It can be summarized by the 4Cs:

    • Communication
    • Critical Thinking
    • Creativity
    • Collaboration

    Reading through this list, you may think, "Hey, those are my classroom goals as an English language teacher!" Finally, the rest of the world has caught up with the modern English language classroom. Of course, when describing these skills, we aren't just talking about teaching English, but skills that can be used to prepare learners for the modern age. This means we want our students to be able to:

    • Perform independently and with groups in a highly technologically advanced atmosphere.
    • Be ready for daily, global interaction.
    • Be capable of adaptive, flexible and creative thinking.
    • Understand how to plan for, build, and include collaboration with peers who are colleagues and experts in the field.

    Students and 21st-century skills

    This goes a bit above and beyond the basics of the walls of the English language classroom. And yet, preparing our students for the 21st century doesn't require a classroom resembling a science fiction movie set. Several teachers have proved that you can embed these skills by utilizing the most important resource available in the classroom.

    Your students.

    Sergio Correra is an inspired young teacher at the Jose Urbina Lopez Primary School on the US Border with Mexico. After a year of teaching uninspired curriculum to disengaged students, he returned to the drawing board. He spent time researching ways to improve student engagement and performance and stumbled across exciting research that could be boiled down to one question: Why? Or rather, getting students to ask the question: "Why?" At the beginning of his next school year, he arranged the desk in a circle, sat his students down and asked: "What do you want to learn about?".

    Using this as the jumping-off point, he encouraged students to ask questions, seek out more information, and find more questions to answer.

    Over the next year, he saw his students' test scores rise, the engagement and enthusiasm improved and he received approval from his principal and fellow educators. With few resources and limited access to technology, he found his students shifting from the lowest testing group in the nation to being ranked among the highest for their performance on standardized tests in the country. One of his students was the highest-performing maths student in the country.

    Mr. Correra was inspired by research and reports based on the work of the Indian educator Sugata Mitra. The principle behind Mr. Mitra's approach is to drive student's curiosity by letting them carry out their own learning. In one of his most famous examples, he walked into a classroom in India with computers loaded with information. He explained to the students, now curious about the big shining boxes that held inside something interesting.

    And then he left the students to it.

    In the course of a year, students had taught themselves everything from English to molecular biology, all without the guidance of a teacher. Rather, they were driven by their natural curiosity, playing off of each other's discoveries to go farther and learn more. Embodying what it means to be self-guided, innovative, collaborative and curious learners.

    Keeping your curriculum up to date

    These students who were given freedom are much more likely to ask questions out of curiosity, motivate themselves and learn without guidance. And while this may be wonderful for learners, this isn't exactly helpful for teachers. To get to the 21st-century skills and inspire motivation, do we have to throw away our syllabus and books and trust only in our learners to motivate themselves?

    Fortunately for those of us who have chosen a career in education, that is not the case. We as educators can take lessons from Mr. Correra and Mr. Mitra and use these as a way to inspire interest and engagement in our own classroom while building these skills in our learners.

    As language teachers, it's a matter of blending the 4Cs more thoughtfully into a student-centered classroom where learners can engage in high-interest content that is relevant, useful, and promotes innovation.

    Take your average prepositions lesson as an example. Even in the best communicative classroom, a teacher may still spend time explaining the rules, setting up the activity and delivering instruction. By applying the 4Cs we can turn this lesson a bit more on its head, making a typical ELL grammar lesson magical.

    For example:

    Collaborate: Start by handing out magazines or picture books. Have the students work together and choose a picture.

    Communication, critical thinking, and creativity: Ask your studentsto work together to create two ways to give directions. One set of directions for a student who is blind. Another set of directions for a student who is deaf.

    Encourage students to think outside the box and think about ways to give directions using a computer, a mobile phone, a television, or a YouTube video. While there may be some L1 use in the classroom, the goal is for the final product to be in English. Stand back and watch your learners go.

    Another way to engage with 21st-century skills using a typical ELL lesson: the "What's your favorite food lesson?" At some point, we have all experienced it.

    Collaborate: In groups, have students create a survey to assess classroom interest in 10 different foods representing different types of meals (breakfast, lunch, dinner, dessert).

    Communication: Once finished, have learners use the information to create a pie or bar graph to communicate the results and determine which meals are the favorite.

    Critical thinking: Have the students compare their answers with answers from other groups. How many differences are there in the reporting? Is the information consistent with the same foods or does it change drastically? Have students compare their results with other teams. Then ask the groups to create a short written or spoken piece to explain how their results differed from other students.

    Creativity: Using the information collected from the class and after analyzing data from other students, have groups work together to create an advertising campaign that will make the foods that students liked least into foods students may like more. For example, if the survey said that most students did not like for breakfast, the group would need to work together to create an advertising campaign to make kim-chi-chigae seem like a tasty choice for breakfast. To do this students should consider what makes certain foods more popular in the class.

    This may require further follow-up interviewing to find out why students like one thing and not another; this information can then be used in the campaign. This lesson may play out over a few days, but in the end, everyone involved will have gotten much more out of the lesson than they had anticipated.

    Both of these examples represent the use of skills in the ELL classroom. Each lesson also embeds, in one way or another, critical STEM skills.

    In the preposition lesson, the students may use engineering and technology to find a better way to give directions. In our favorite foods lesson, students engage with science (and a bit of sociology) and mathematics. Altogether it becomes a rounded classroom experience where teachers have an active role as facilitators and students become inspired, self-guided learners who still manage to work inside of the confines of the curriculum.

    In the end, 21st-century skills, and using them in the classroom is not really about teaching at all. These skills are truly ones that will spell success for our learners in the future, leading them to be capable, Independent and curious individuals.

    Our real challenge as educators is to model a desire to embrace the known, the unknown, and the just plain unknowable. As Alwin Toffler, writer and futurist, put it: "The illiterate of the 21st century will not be those who cannot read and write, but those who cannot learn, unlearn, and relearn."