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 laughing together while having drinks

    10 English words and slang terms you should know

    By

    Not everything can be taught in the classroom – that’s why we’ve put together a list of 10 English words, slang terms and figures of speech for you to sprinkle into your English conversations. Not sure how to use them? Don’t worry, we’ve included definitions and examples of how to use them in a sentence.

    Earworm

    A song or tune that, once you’ve heard it, is stuck in your head.

    Use it: “That new Taylor Swift song is such an earworm!”

    Staycation

    Spending your holiday in your hometown rather than traveling abroad. Often spent relaxing around the house or doing activities in the local area.

    Use it: “I’m having a staycation this summer, as I’m trying to save money.”

    Webisode

    An episode or series created exclusively for online viewing. This can be part of a web series or used to promote a television series.

    Use it: “There’s a new Breaking Bad webisode online, have you seen it?”

    Crowdfunding

    Funding a project or business venture by asking a large number of people (typically online) to invest a small amount of money – usually via websites such as Kickstarter and Indiegogo.

    Use it: “We raised enough money to launch our business using crowdfunding.”

    Glamping

    Glamorous camping! Avoiding any rough conditions with luxurious facilities and accommodation, such as a yurt or cabin.

    Use it: “We’re going to be glamping at Glastonbury this year.”

    Lookalike

    Something or someone that closely resembles something else, often used to describe someone who looks very similar to a celebrity.

    Use it: “Have you seen the Prince William and Kate Middleton lookalikes over there?”

    Handover

    This word has a more political significance, in terms of gaining land or ownership. However, its modern usage is commonly in the workplace: The act of passing over control or responsibility to another person while you are off work on holiday or leaving a job.

    Use it: “I’ll send my notes in a handover email so you can continue the project while I’m away.”

    Meh

    When something is a little uninspiring or dull. Also a word you could use to describe your lack of interest or indifference. It’s basically a verbal shrug.

    Use it: “The film was a bit meh.”

    Binge-watch

    Watching multiple episodes of a TV show, one after another, in a single sitting. Usually, with a DVD box set or using online streaming.

    Use it: “I’m planning to binge-watch the entire series of Game of Thrones this weekend!”

    Spill the tea

    When someone 'spills the tea' they are telling you all the latest news or gossip.

    Use it: “Please spill the tea about last week's party!"

  • A pile of open books on top of each other

    Using authentic material from the real world to teach English

    By

    There are lots of resources available to English teachers today: from textbooks to online teaching tools, they can all aid and enrich English lessons. Many ESL teachers also introduce authentic English material into their lessons to expose learners to the language as it is spoken in the real world.

    Authentic material is any material written in English that was not created for intentional use in the English classroom. Using this content for teaching English can make the teaching experience even more engaging, imaginative and motivating for students. It can also be useful to elicit genuine responses from English language learners.

    The great thing about using authentic material is that it is everywhere, which makes it easy to find, and simple for learners to practice English in their own time. Remember that it isn’t limited to articles from newspapers and magazines. Songs, TV programs and films, radio and podcasts, leaflets, menus – anything written in English constitutes authentic material.

    Selecting authentic material

    The best content to select depends on the learners, their level of English and the course content the English teacher wishes to focus on. It’s also a good idea to find out the learners’ interests – after all, there’s no point trying to get students fascinated by a text on the latest sci-fi movie if they’re all fans of action films.

    The materials should reflect a situation that a student may face in an English-speaking environment – this will help them transition into a world where English is the norm. In this world, people use abbreviations, body language is important and they’ll use 'filler' sounds – such as 'ummm' – when they are speaking English – and learners will encounter these in authentic material.

    It’s important not to overwhelm learners with the first piece of authentic material. So, choose articles, songs or sections of TV programs or movies that aren’t too difficult to understand or take too long to get through.

  • a young boy and a young girl sat at desks in a classroom, smiling and looking at another child in front of them

    Five ways to promote friendship in your English language classroom

    By Joanna Wiseman

    There is a strong link between well-being and friendship, which is just as accurate for children as it is for adults. that children with stable friendships are happier, more able to cope with stress, and have higher self-esteem. Moreover, too, and children who experience friendship adjust more easily to school and perform better academically. School friendships are also a valuable way of learning social skills like sharing, resolving conflict, and engaging with peers positively.

    Having friends is an important part of school life, and teachers can play a significant role in creating a positive classroom culture and helping children and young people to form friendships. How can you promote friendships between your students? Here are some ideas:

    1. Make friendship a central theme in your classes

    If there is an example of a good friendship in a book you are reading with students or in your lesson materials, draw your students’ attention to it. For instance, The Jungle Book is an excellent example of a story about friendship. Encourage your students to think critically about the friendships that they read about. You can ask questions like:

    • What are some things a good friend does?
    • What are the qualities of a good friend?
    • What words do you associate with friendship?

    By discussing friendship regularly in the classroom, your students will learn about the behavior and characteristics of being a good friend.

    2. Create opportunities for interaction

    You can create lots of opportunities for students to build friendships with one another during class time. Design activities that call for pair or group work, and include at least one or two in every lesson. Focusing on a common goal or problem is a great way to encourage your students to bond with one another.As a bonus, this collaborative way of working promotes important 21st century skills like communication and problem-solving.

    Another way of promoting friendships between different groups of students is moving them around. Adjust your seating plan regularly to ensure that all your students interact with and work alongside different classmates, to promote positive, friendly classroom vibes.

    3. Discuss and model good behavior

    Friendship is a social skill that children need to learn – and you can help by teaching them. Be explicit about exactly what you expect from them. Saying, “Be kind” is an abstract, vague concept that children might struggle to put into practice. Instead, give them concrete examples of behavior, such as:

    • take turns when playing
    • speak respectfully
    • share pens or other resources

    When you see a student engaging in these behaviors, draw attention to them and praise them.

    But to really convey the importance of school friendships and kind behavior, it’s not enough to tell them. As the teacher, you must model the behavior you’d like to see in your students. Be consistently positive and upbeat in your interactions with students, thank your learners when they offer help with something, and try to refrain from sounding impatient (even when you are!). All these steps will help to build a positive classroom culture where students feel secure, supported and happy.

    4. Help to navigate difficult situations

    Conflict is an inevitable part of school life, but you can help students to navigate arguments and other difficult situations in the classroom. If two students argue, you can help them to resolve it with the following steps:

    • Separate the students to give them time to calm down.
    • Have a conversation with them. Ask for their perspective on the conflict, and find out how their day has been in general. Sometimes, you can better understand a student’s reaction when you look at the bigger picture. Ask them how they feel, and how they could resolve the situation.
    • Bring the students together again to discuss things and find a resolution together. Reconciliation is the goal.

    Following these simple steps teaches children a framework for resolving conflict and gives them the tools to process strong emotions.

    5. Do some friendship-focused activities

    An excellent way to promote a positive classroom culture is to do friendship-focused activities with your students:

    You could do a Venn diagram activity, where students work in pairs to discuss and write down things they have in common and areas of difference. It’s good to pair students who don’t spend much time together for this activity.

    Another positive activity is a 'Honey Roast'. Give students enough squares of paper to have one for each of their classmates. Get them to write their classmates’ names on the paper, and then, on the other side, write down a compliment or something they like about that person, for example, “I like your handwriting”, or “You always use kind words”. Collect the pieces of paper and read out some nice examples to the class. Alternatively, give them directly to the students to read to themselves.