Can computers really mark exams? Benefits of ELT automated assessments

Pearson 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. 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. 

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 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.

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 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.

Examples of AI assessments in ELT

At Pearson, 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 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)

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?'.

More blogs from Pearson

  • Students in uniform sat at tables in a classroom with a teacher at the front talking to them all.

    Bridging the gap: How to equip English learners with workplace-ready language skills

    By Pearson Languages
    Reading time: 5 minutes

    Educators worldwide are faced with a vital challenge: closing the language education gap between traditional schooling and the practical language requirements of the modern workplace. With English established as the language of international business and in light of our ground-breaking new research, the need for education to address this disparity has never been more critical.

    In this blog post, we'll explore why teaching English through a lens of real-world application is necessary, what our research shows about the current gap in language education, and some ideas for how English teachers can integrate employability-focused lessons into their own English teaching curriculum.

  • A teacher helping students at a table. The GSE ambassador logo is to the left of them.

    Empowering future educators: Integrating the GSE into pre-service teacher training

    By Belgin Elmas
    Reading time: 6 minutes

    When we used to go somewhere by car, my son, who was just three years old, would repeatedly ask me, "How far do we need to go?" every five minutes. He was curious to know where we were and how close we were to our destination. Even though the answer was just a number, it would satisfy him and relieve his curiosity.

    For language learners, it is important to maintain a high level of curiosity about progress and the distance needed to cover in their language learning journey. This can help identify areas for improvement and help them stay motivated. For teachers, it is also important to have a tool that can assist their students in visualizing their language learning goals more concretely. The Global Scale of English (GSE) is a valuable resource for this purpose. It not only indicates learners' current proficiency levels but also provides learning outcomes to help them progress in their abilities. The scale ranges from 10 to 90 and offers a personalized pathway for improvement in each individual skill based on global research. By using the GSE, both learners and teachers can work together to achieve language learning success.

    I believe the GSE is one of the most valuable resources a language teacher needs in teaching English; the learning outcomes provide clear guidance on what to teach, tailored to the specific needs of learner groups. With five options designed for pre-primary, young, general adult, professional and academic English learner groups, the GSE offers educators clear paths to customize their teaching strategies effectively. It also assists teachers in motivating their students by showing their progress regularly, which provides precious support throughout their learning journey.

    I also believe that the sooner we introduce teachers to this valuable tool in their teaching careers, the better equipped they will be to help their learners. With this belief in mind, we integrated the GSE into our pre-service teacher education program, making it the cornerstone for lesson planning and assessment. This blog aims to explain our implementation process at TED University's Education Faculty English Language Teaching Department, hoping to provide a model for other programs interested in adopting a similar approach.  

    Implementing the GSE

    Our implementation process started with conducting in-service training sessions for the faculty members, many of whom were also unfamiliar with the GSE. To ensure comprehensive understanding, we organized meetings with the teacher trainers responsible for teaching the methodology courses. These sessions consisted of in-depth discussions on the nature of the GSE, its significance in language teaching and practical guidance on integrating it into the curriculum we were following.

    As the second step, we designed a lesson plan to be used for the first methodology course our pre-service teacher trainees would undertake for the same objective we had for in-service teacher training sessions. In this initial lesson, we started by discussing the aims of CEFR and GSE, highlighting their differences.

    Then, we facilitated discussions on how GSE helps to monitor the progress of learners, what the main features are that the GSE has been built upon, and most importantly, we focused on increasing our future teachers' consciousness on how learning objectives can help a teacher. The lesson proceeded with an introduction to the GSE Toolkit, clarifying its categories, contained skills, and the target language learners it caters to. After providing diverse samples across various skills and outcomes, we demonstrated how our pre-service teachers can find learning objectives within the scale and how they can use them. 

    The lesson then transitioned into practical exercises designed to familiarize the teachers with the toolkit. Through guided instructions, such as selecting a target group, a skill, and a proficiency range, we prompted them to engage in activities aimed at perceiving the usefulness of the toolkit. We then asked them to report on some chosen parameters, such as the selected range, the number of objectives identified, and the potential text materials applicable to the chosen skill (e.g., reading comprehension). We followed a similar process for the other skills. 

    The second part of the lesson illustrated how different teaching materials were mapped with the GSE framework, utilizing sample coursebooks like Speakout, Roadmap and Startup. The lesson concluded with getting reflections from the pre-service teachers on their perceptions of the GSE. We gathered their insights on its usefulness, including its impact on curriculum design, teaching methodologies, and skill assessment practices.

    After being introduced to the GSE, we asked our pre-service teachers to integrate it into all their teaching-related courses. They now plan their lessons based on the learning outcomes provided in the toolkit, benefitting from the additional resources it offers to enhance their instructional practices. Teaching Skills, Teaching English to Young Learners, and Material Development can be given as samples of the courses the GSE was integrated into; there is no need to mention that all teaching practicum-related courses are in the integration part as well.

    The benefits 

    What did we gain by integrating the GSE into our pre-service teacher education program? Quite a few significant benefits, actually. Firstly, it standardized the language and terminology used throughout the department; when we refer to terms like 'learning outcomes', 'proficiency of language learners' or 'learner progress', everyone understands the set of terms uniformly across our department. No need to mention that our pre-service teachers gained the privilege of being introduced to a widely recognized toolkit in the field. While their peers may not yet be familiar with the GSE, our students gain early exposure to this valuable resource. Incorporating the GSE into our program also has allowed our pre-service teachers access to a range of valuable resources.

    In addition to the GSE Toolkit, resources such as Text Analyzer or instructional materials aligned with the GSE help our future teachers plan and deliver language instruction more effectively. As a result, our pre-service teachers enter the field with a deeper understanding of language assessment, proficiency levels, and learner needs.

    Next steps

    What's next? There's still much to accomplish and a considerable journey ahead of us. Currently, our primary focus is on making our initiatives more public, aiming to share our experiences with other pre-service teacher education programs considering integrating the GSE into their curriculum. In addition, introducing the GSE to in-service teacher programs in Turkey and globally could also be valuable for enhancing language teaching practices and the professional development of language teachers worldwide.

    Publishing articles, presenting at conferences, hosting workshops, or developing online resources might be some of the sources for sharing our practices. Increasing the awareness of policymakers, school administrators, and language teachers on the GSE and highlighting the benefits of using a standardized granular framework like the GSE can encourage broader adoption and implementation across educational settings. Collaboration opportunities with other institutions and stakeholders in language education will help all of us to reach our destination more quickly and efficiently. Finally, research on the impact of the GSE in language education is required to refine our approaches.

    As a result, we are very pleased with the integration of the GSE into our teacher education program, as it has paved the way for significant advances. While recognizing there's still a considerable journey ahead, we also celebrate the progress we've made thus far and are curious about the other possible opportunities that lie ahead.