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

  • Woman sat at a desk with a laptop, tablet and open notepads studying

    6 language learning techniques for beginners

    By

    Reading time: 4 minutes

    So you’ve just started to learn a new language (or just set up a resolution to learn one), you're not alone; every day there are embracing the challenge of mastering a language. It can be tricky to know where to start, and sometimes the biggest learning hurdle.

    No matter what language you're trying out (and whatever your native language), there are always solid methods to help start your journey off and help reach your language learning goals. Here are some suggestions to help you get started.

    Chunking technique

    Rather than attempting to memorize lengthy lists of words, it's more effective to break them down into smaller, more manageable chunks. You can group the words by themes or categories, such as food, colors or daily activities. Additionally, you can use mnemonic devices or create associations to help you remember them more efficiently.

    For example, if you're trying to learn colors, you could use the acronym "ROYGBIV" and make a phrase out of that, like ‘Richard of York gave battle in vain’ to remember the colors of the rainbow: red, orange, yellow, green, blue, indigo and violet. You can make whatever acronyms or phrases are easiest for you to remember.

    This technique can also be used to remember rules or concepts. By associating them with memorable phrases, images or stories, they become easier to recall and apply in practical situations.

    Spaced Repetition System (SRS)

    Use spaced repetition systems like Anki or Quizlet to create flashcards for vocabulary. These systems use algorithms that show flashcards at intervals based on your familiarity with the words. Review flashcards regularly, focusing more on unfamiliar words to reinforce memory retention.

    To create effective flashcards, it is important to focus on quality over quantity. Instead of trying to memorize large amounts of words at once, start with a smaller set of words and gradually add more as you become more comfortable. When creating your flashcards, include both the word and its definition. You can also include example sentences or images to help you remember the word more easily.

    The more you practice something regularly the more likely it is to stick in your . You’ll be surprised how much you can retain over time with this technique that’s based on science.

    Pomodoro Technique

    A classic but essential technique. Divide your study time into short, focused intervals using the Pomodoro Technique. Set a timer for 25 minutes of concentrated language practice, followed by a 5-minute break. Repeat this cycle and take a longer break after every 4 cycles (2 hours).

    This method boosts productivity and maintains focus during study sessions. It is great for those days when your attention span isn’t as sharp as usual. Find an online Pomodoro .

    Visual learning aids

    If you are feeling overwhelmed by the amount of information you are trying to learn, creating visual aids such as mind maps and infographics can be a helpful way to simplify complex concepts and make them easier to understand.

    For example, when studying a new language, you may find it helpful to create a mind map that breaks down the different grammar rules, verb conjugations and key phrases you need to know. This can help you see how all of the different elements fit together and make it easier to remember them when you need to use them. It can be a great way to also notice patterns, which can be helpful for understanding a concept or language rule.

    Vocabulary notebook

    Designate a notebook or use digital tools to create avocabulary repository. Divide it into sections based on themes. For example, you could have a section for business vocabulary, another for scientific terms, and so on. This will help you to organize your learning and make it easier to find and review specific words and phrases.

    As you come across new words, be sure to add them to your vocabulary repository right away. Include the word, its definition and an example sentence to provide context. You can also add images or audio recordings to help reinforce your understanding of the word.

    The great thing about designing your own book is that you can present it however you want and in whatever way works best for you. Some people find the act of writing their learnings useful to remember what they’ve learned.

    Regularly reviewing your vocabulary repository will help you retain the words you have learned and expand your knowledge over time. So make sure to set aside some time each week to review your vocabulary and add new words as you come across them.

    Listen and repeat

    Find beginner-friendly podcasts, , TV shows or audio dialogues in the target language. Listen attentively and pause at intervals to repeat what you've heard. Focus on mimicking the speaker's pronunciation and rhythm. This technique aids in comprehension and speaking fluency.

    There are many free resources available online that can help you with this type of listening practice. YouTube is a great place to start, as there are many beginner-friendly clips available in a wide variety of languages; for example, if you're learning Spanish, there are plenty of podcasts available online and on Spotify.

    These specific language learning methods, when incorporated into your language study routine, can significantly help aid your progress as a beginner and keep you on track. Experiment with different methods to find what works best for your learning style and stick to it.

    Don't forget to try out different language learning strategies, even the ones that may seem weird or unusual. You might be surprised at what you find works well in improving your language skills.

    If you're trying to learn English, make sure to read our blog post 6 easy ways to learn English or 3 ways to learn new English words.

  • Business woman presenting and discussing with two people in front of her

    How to recruit more effectively: leveraging language assessment AI

    By Samantha Ball
    Reading time: 3 minutes

    There arewhy recruiters use artificial intelligence (AI) tools in their hiring process: to save time, provide valuable insights and to make their jobs easier.

    The recruitment process is vital to any thriving business, but it can be time-consuming and labor intensive. Sourcing candidates, screening resumes, conducting interviews and making hiring decisions can be stop-start, with some time-wasting tasks and reprocessing. However, as technology continues to evolve, the role of AI in recruitment is becoming increasingly important.

    With the help of AI, Talent Acquisition leads can improve their recruiting processes, save time and find better-quality candidates. believe AI greatly enhances talent acquisition and retention.

  • A teacher stood at a students desk helping them

    How the GSE can help teachers personalize activities

    By

    Reading time: 4.5 minutes

    Teaching is an art form that thrives on adaptation and personalization. When dealing with language instruction, ensuring that each student is engaged and effectively learning is of paramount importance. In my experience as a teacher, I have learned that we should always teach our students rather than the coursebook or the syllabus. I think most teachers would agree with this.

    However, it may be challenging to adapt activities to cater to our learners’ needs. What does personalizing an activity mean? How can we make it more accessible to our English learners? One would think that making the answers more obvious can be the way to go. Yet, this does not really help students learn and make progress. That's where the Global Scale of English (GSE) comes in as a valuable tool for personalizing teaching activities.

    The essence of personalized learning

    Personalizing an activity in language teaching does not simply mean making the responses more obvious. Instead, it's about tailoring the exercise to elevate the student's learning experience and potential for progress. This demands an insightful approach during the preparation phase of any given lesson.

    Utilizing the GSE in language teaching

    Let’s analyze this listening activity at A2 level for a group of adults:

    Audio script example:

    Emma: Are you working on the Media project?

    Vic: Yes. I may start working on a new project in a couple of weeks, but for now I’m writing the objectives for Media. Why?

    Emma: Well, Adam wants to see the photos for the project. He needs them for the ads.

    Vic: Oh, they’ll be ready next week. OK?

    Emma: Awesome! Thanks. Any plans for the weekend?

    Vic: Well, I have to work on Saturday. We’re taking the Media pictures in the morning, but we’re just going to have fun at the beach in the afternoon.

    Emma: Nice!

    Vic: What about you? What are you doing this weekend?

    Emma: I’m going to a concert on Sunday at 3 pm.

    Vic: That sounds fun!

    Listen and write T (true) or F (false)

    1. Vic is working on a new project.

    2. Vic is working on Saturday morning.

    3. Emma is going to a concert on Sunday evening.

    GSE Descriptors

    Upon dissecting this example by the GSE descriptors, we can identify the learning objectives that align with an A2 level:

    • Can identify simple information in a short video, provided that the visual supports this information and the delivery is slow and clear. (GSE 30)

    • Can identify basic factual information in short, simple dialogues or narratives on familiar everyday topics, if spoken slowly and clearly. (GSE 32)

    • Can understand the main information in short, simple dialogues about familiar activities, if spoken slowly and clearly.(GSE 33)

    • Can identify key information (e.g., places, times) from short audio recordings if spoken slowly and clearly. (GSE 33)

    We know that learners should be given a global task first for overall listening, which is also one of the communicative objectives in the Global Scale of English: