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. PTE Academic and Versant tests – 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.
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.
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.
Our AI writing scoring uses a technology called latent semantic analysis. 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.
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.
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.
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 assessment to 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.
At Pearson, we have developed a range of assessments using AI technology.
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.
The Pearson Test of English Academic 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.
Pearson English International Certificate (PEIC) also uses automated assessment technology. With a two-hour test available on-demand to take at home or at school (or at a secure test center). Using a combination of advanced speech recognition and exam grading technology and the expertise of professional ELT exam markers worldwide, our patented software can measure English language ability.
Read more about the use of AI in our learning and testing here, or if you're wondering which English test is right for your students make sure to check out our post 'Which exam is right for my students?'.
At Pearson Languages, 2024 has been a landmark year full of innovation, connection, and impactful resources for businesses worldwide. We’ve worked on so many things with the aim to empower global workforces and help organizations unlock the potential of language skills to drive business success. Here's how we made a difference this year.
As the new year approaches, it's the perfect time to reflect on our teaching practices and plan engaging, effective lessons for our English as a Second Language (ESL) students. Thoughtfully crafted lesson plans can make a significant difference in the learning outcomes and engagement levels of your students. Whether you're teaching young children, teenagers, or adults, the principles of effective lesson planning remain consistent. Here are some ideas, hints and tips to help you create dynamic and successful ESL lessons for students of all ages.
Begin each lesson with clear, achievable objectives. What do you want your students to learn by the end of the lesson? Objectives provide a roadmap for both you and your students, ensuring that everyone is focused and aware of the goals. For example, an objective might be "Students will be able to use past tense verbs to describe their weekend activities." Clear objectives provide direction and help you measure student progress.
To cater to different learning styles and keep students engaged, incorporate a mix of teaching methods and activities. Here are a few ideas:
Authentic materials—such as newspapers, menus, brochures and videos—expose students to real-world language and contexts. These materials can make lessons more interesting and relevant, helping students see the practical application of their language skills. Even better, they’re everywhere, so easy to find. Here are some more suggestions for how to select and use authentic materials in your English language teaching.
Teachers are already used to leveraging technology to enhance lessons utilizing online resources, language learning apps and interactive platforms to create a dynamic learning environment. Why not take this a step further by using AI to create your own resources. Take a look at our blog on How to make the most of AI in the classroom for some more ideas.
How can teachers use the Global Scale of English (GSE) and AI to help students set and achieve language learning goals for the new year?
As the new year rolls around, it’s the perfect time for students to set fresh language learning goals. But for teachers, it’s not just about inspiring students—it’s about giving them clear, measurable goals that they can actually achieve. That’s where the GSE, a very powerful tool, comes in. It can help teachers create personalized learning paths based on where students are right now and guide them toward their language goals throughout the year. Let’s dive into how the GSE can work to boost student progress.
The GSE is a precise framework that measures English proficiency with remarkable detail. Each score on the GSE aligns with specific speaking, listening, reading and writing competencies. For instance, a student with a GSE score of 50 might handle everyday conversations comfortably (B1 level), while a score of 75 indicates functioning at a more advanced level (C1).
What sets the GSE apart is its granularity—it goes beyond general levels of "intermediate" or "advanced," allowing teachers to identify exactly what their students can do at any stage. This level of detail enables teachers to set targeted, skill-specific goals for every learner, ensuring personalized and purposeful progression.
Before setting goals, it’s important to determine each student’s current standing. The GSE is an excellent tool for this because it provides a detailed breakdown of a student's skills. Teachers can use GSE-aligned assessments to pinpoint strengths and weaknesses, which gives a clearer picture than just knowing if a student is at an “intermediate” or “advanced” level.
Once you know where students are, you can set a baseline. For instance, if a student’s reading score is 52, you’ll know that they are likely in the B1 range, and you can target specific skills (like improving vocabulary or understanding main ideas) to move them forward.
Now that you know where each student stands, it's time to set some goals. These should be realistic, measurable and achievable based on their current level and the time span involved. The key is to pick goals that will push them to improve without overwhelming them. The GSE has detailed descriptions of what students can do at each level. You can pinpoint specific skills that need attention by looking at these descriptors. We know that large goals can feel intimidating, so break them into smaller, manageable chunks. Here, the GSE is an amazing resource, thanks to its granularity.
Using the GSE Learning Objectives (LOs) in conjunction with an LLM (Large Language Model) opens up a world of possibilities for creating focused activities at the right level for each student. Here are some key points on how this combination enhances personalized learning:
By combining the GSE LOs and harnessing the power of an LLM like ChatGPT, teachers can create personalized activities that cater to individual students' language needs, promote active learning, and foster continuous improvement.
Setting goals is just the start—tracking progress and adjusting those goals as needed is just as important. Throughout the year, teachers should regularly check in with students to make sure they’re on track. How can we monitor and adjust? Here are some tips.
Teachers should schedule regular one-on-one sessions with students to review their progress. The GSE can clearly show students their progress.
If students are achieving their goals faster than expected, adjusting their targets is important to keep them challenged. If they’re struggling, the goals might need to be more achievable, with smaller, more gradual steps.
Using the GSE can help students set clear, measurable goals and steadily progress throughout the year. By assessing where students are starting, setting specific GSE-based goals, creating personalized learning paths with AI, and continuously tracking progress, teachers can create a more dynamic and effective learning experience for their students. The new year is the perfect opportunity to help students improve their English and achieve their goals—and with these tools, teachers have everything they need to guide students toward success.
