Explaining computerized English testing in plain English

ɫèAV Languages
a pair of hands typing at a laptop

Research has shown that automated scoring can give more reliable and objective results than human examiners when evaluating a person’s mastery of English. This is because an automated scoring system is impartial, unlike humans, who can be influenced by irrelevant factors such as a test taker’s appearance or body language. Additionally, automated scoring treats regional accents equally, unlike human examiners who may favor accents they are more familiar with. Automated scoring also allows individual features of a spoken or written test question response to be analyzed independent of one another, so that a weakness in one area of language does not affect the scoring of other areas.

was created in response to the demand for a more accurate, objective, secure and relevant test of English. Our automated scoring system is a central feature of the test, and vital to ensuring the delivery of accurate, objective and relevant results – no matter who the test-taker is or where the test is taken.

Development and validation of the scoring system to ensure accuracy

PTE Academic’s automated scoring system was developed after extensive research and field testing. A prototype test was developed and administered to a sample of more than 10,000 test takers from 158 different countries, speaking 126 different native languages. This data was collected and used to train the automated scoring engines for both the written and spoken PTE Academic items.

To do this, multiple trained human markers assess each answer. Those results are used as the training material for machine learning algorithms, similar to those used by systems like Google Search or Apple’s Siri. The model makes initial guesses as to the scores each response should get, then consults the actual scores to see well how it did, adjusts itself in a few directions, then goes through the training set over and over again, adjusting and improving until it arrives at a maximally correct solution – a solution that ideally gets very close to predicting the set of human ratings.

Once trained up and performing at a high level, this model is used as a marking algorithm, able to score new responses just like human markers would. Correlations between scores given by this system and trained human markers are quite high. The standard error of measurement between ɫèAV’s system and a human rater is less than that between one human rater and another – in other words, the machine scores are more accurate than those given by a pair of human raters, because much of the bias and unreliability has been squeezed out of them. In general, you can think of a machine scoring system as one that takes the best stuff out of human ratings, then acts like an idealized human marker.

ɫèAV conducts scoring validation studies to ensure that the machine scores are consistently comparable to ratings given by skilled human raters. Here, a new set of test-taker responses (never seen by the machine) are scored by both human raters and by the automated scoring system. Research has demonstrated that the automated scoring technology underlying PTE Academic produces scores comparable to those obtained from careful human experts. This means that the automated system “acts” like a human rater when assessing test takers’ language skills, but does so with a machine's precision, consistency and objectivity.

Scoring speaking responses with ɫèAV’s Ordinate technology

The spoken portion of PTE Academic is automatically scored using ɫèAV’s Ordinate technology. Ordinate technology results from years of research in speech recognition, statistical modeling, linguistics and testing theory. The technology uses a proprietary speech processing system that is specifically designed to analyze and automatically score speech from fluent and second-language English speakers. The Ordinate scoring system collects hundreds of pieces of information from the test takers’ spoken responses in addition to just the words, such as pace, timing and rhythm, as well as the power of their voice, emphasis, intonation and accuracy of pronunciation. It is trained to recognize even somewhat mispronounced words, and quickly evaluates the content, relevance and coherence of the response. In particular, the meaning of the spoken response is evaluated, making it possible for these models to assess whether or not what was said deserves a high score.

Scoring writing responses with Intelligent Essay Assessor™ (IEA)

The written portion of PTE Academic is scored using the Intelligent Essay Assessor™ (IEA), an automated scoring tool powered by ɫèAV’s state-of-the-art Knowledge Analysis Technologies™ (KAT) engine. Based on more than 20 years of research and development, the KAT engine automatically evaluates the meaning of text, such as an essay written by a student in response to a particular prompt. The KAT engine evaluates writing as accurately as skilled human raters using a proprietary application of the mathematical approach known as Latent Semantic Analysis (LSA). LSA evaluates the meaning of language by analyzing large bodies of relevant text and their meanings. Therefore, using LSA, the KAT engine can understand the meaning of text much like a human.

What aspects of English does PTE Academic assess?

Written scoring

Spoken scoring

  • Word choice
  • Grammar and mechanics
  • Progression of ideas
  • Organization
  • Style, tone
  • Paragraph structure
  • Development, coherence
  • Point of view
  • Task completion
  • Sentence mastery
  • Content
  • Vocabulary
  • Accuracy
  • Pronunciation
  • Intonation
  • Fluency
  • Expressiveness
  • Pragmatics

More blogs from ɫèAV

  • Two women sit at a desk, one pointing at a document, in a discussion, with a plant and window in the background.

    My lifelong learning journey: Why learning English never stops

    By
    Reading time: 4 minutes

    Why did I want to learn English? When I was 9 years old, I became sick of French at home and I decided to go for the "opposite": English. I fell in love with it the moment I started learning. Though I could not see the point in many activities we were asked to do, such as turning affirmative sentences into negative and questions, or transforming conditional statements, I was good at it and hoped that at some point, I would find the meaningfulness of those exercises.

    Overcoming challenges in English language learning

    I kept on learning English, but the benefits were nowhere to be seen. In my school, classes are monolingual and teachers and students all share the same mother tongue. However, translanguaging was not an option. I even remember being told to forget Spanish, my mother tongue, which was as ridiculous and impossible as asking me to forget I have two legs. Before I finished secondary school, I knew I wanted to take up a career that had English at its core.

    From student to teacher: Finding purpose in teaching English

    I started the translators programme, but soon I saw that it was teaching that I loved. I changed to that and I have never stopped teaching or learning. All the pieces fell into place as I was asked to use English meaningfully, as I started focusing on meaning rather than on grammar. And I made this big learning insight one of the principles and main pillars of teaching. Some heads of school wondered why I would not follow the coursebook. My answer, since then, has been: I teach students, not a book or a syllabus. Because I was focusing on using English with a purpose – using it meaningfully – the results were excellent, and my students were using the language. And they passed the tests they needed to take.

    Teaching English with meaning: Moving beyond the coursebook

    I used coursebooks, as every other teacher did, but continued to make changes that I thought would be beneficial to my learners. As I taught Didactics at university in the Teacher Education Programme, I was invited by some publishing houses to give feedback on new coursebooks. As I was told, the feedback proved to be useful, and I was asked to start modifying international coursebooks to fit the local context and design booklets to provide what was missing in these adaptations, until I was finally invited to write a series for Argentina.

    In all the series I’ve written, my first comment has always been: “This is the result of my experience in several different classrooms, with different students from various backgrounds. This is a series by a teacher and for teachers and their learners. The focus is not on teaching, but on what is necessary for students to learn."

    Flexibility has always been at the core of these series and my teaching as well. Sometimes students need more work on something, and in the Teacher’s book I included several suggestions for further activities, which I called “building confidence activities”.

    Flexible teaching strategies and confidence-building activities

    As I got involved with the GSE, I saw how it can help students learn much better, and how it can support teachers as they help learners. How so? Because it starts with a focus on using English rather than on learning about it, that is, learning about its grammar. I’ve shared my views on it with every colleague I can and it has been the topic of several presentations and national and international conferences. It’s a fantastic resource for both teachers and learners, but also for the wider educational community. When the scales were finally published, I remember thinking, “Oh my, I was born in the wrong century!”

    I am still teaching English – working at schools as a consultant, designing professional development projects and implementing them, and yes, actually working in classrooms, teaching learners. After many years of teaching English, and still loving it, the best advice I can give is this:

    Advice for English teachers

    Teachers, we’re blessed in that we do what we love, and despite its challenges and hard times, teaching is absolutely rewarding. Nothing can compare to the expression on a student’s face when they've "got it".

    Remember to focus on meaning, help learners become aware of what they already know and set a clear learning path that will keep you and them motivated. The GSE is the best resource and companion for this.

  • A teacher sat with young students while they work and hold crayons

    Icebreaker activities for the beginning of the school year

    By
    Reading time: 3 minutes

    The beginning days of school are both exciting and occasionally nerve-wracking for teachers and students alike. Everyone is adjusting to new faces, routines and a fresh environment. As a teacher, you can help make this shift smooth, inviting and enjoyable. One effective way to achieve this is by using icebreaker activities.

    Icebreakers are simple games or activities that help students get to know each other, feel comfortable and start building a positive classroom community. When students feel connected, they are more likely to participate, help each other and enjoy learning. Here are some easy-to-use icebreaker activities and tips for making the beginning of the school year memorable for everyone. Here are just a few ideas for icebreakers you can use in your classroom.

  • A teacher with students stood around him while he is on a tablet

    How AI and the GSE are powering personalized learning at scale

    By
    Reading time: 4 minutes

    In academic ops, we’re always finding the balance between precision and practicality. On one side: the goal of delivering lessons that are level-appropriate, relevant and tied to real learner needs. On the other hand, we juggle hundreds of courses, support teachers, handle last-minute changes and somehow keep the whole system moving without losing momentum or our minds.

    That’s exactly where AI and the Global Scale of English (GSE) have changed the game for us at Bridge. Over the past year, we’ve been using AI tools to streamline lesson creation, speed up course design and personalize instruction in a way that’s scalable and pedagogically sound.

    Spoiler alert: it’s working.

    The challenge: Customization at scale

    Our corporate English learners aren’t just “students”. They’re busy professionals: engineers, sales leads, analysts. They need immediate impact. They have specific goals, high expectations and very little patience for anything that feels generic.

    Behind the scenes, my team is constantly:

    • Adapting content to real company contexts
    • Mapping GSE descriptors to measurable outcomes
    • Designing lessons that are easy for teachers to deliver
    • Keeping quality high across dozens of industries and levels

    The solution: Building personalized courses at scale

    To address this challenge, we developed an internal curriculum engine that blends the GSE, AI and practical, job-focused communication goals into a system that can generate full courses in minutes.

    It is built around 21 workplace categories, including Conflict Resolution, Business Travel and Public Speaking. Each category has five lessons mapped to CEFR levels and GSE descriptors, sequenced to support real skill development.

    Then the fun part: content creation. Using GPT-based AI agents trained on GSE Professional objectives, we feed in a few parameters like:

    • Category: Negotiation
    • Lesson: Staying Professional Under Pressure
    • Skills: Speaking (GSE 43, 44), Reading (GSE 43, 45)

    In return, we get:

    • A teacher plan with clear prompts, instructions and model responses
    • Student slides or worksheets with interactive, GSE-aligned tasks
    • Learning outcomes tied directly to the descriptors

    Everything is structured, leveled and ready to go.

    One Example: “Staying Organized at Work”

    This A2 lesson falls under our Time Management module and hits descriptors like:

    • Reading 30: Can ask for repetition and clarification using basic fixed expressions
    • Speaking 33: Can describe basic activities or events happening at the time of speaking

    Students work with schedules, checklists and workplace vocabulary. They build confidence by using simple but useful language in simulated tasks. Teachers are fully supported with ready-made discussion questions and roleplay prompts.

    Whether we’re prepping for a quick demo or building a full 20-hour course, the outcome is the same. We deliver scalable, teacher-friendly, learner-relevant lessons that actually get used.

    Beyond the framework: AI-generated courses for individual learner profiles

    While our internal curriculum engine helps us scale structured, GSE-aligned lessons across common workplace themes, we also use AI for one-on-one personalization. This second system builds fully custom courses based on an individual’s goals, role, and communication challenges.

    One of our clients, a global mining company, needed a course for a production engineer in field ops. His English level was around B1 (GSE 43 to 50). He didn’t need grammar. He needed to get better at safety briefings, reports and meetings. Fast.

    He filled out a detailed needs analysis, and I fed the data into our first AI agent. It created a personalized GSE-aligned syllabus based on his job, challenges and goals. That syllabus was passed to a second agent, preloaded with the full GSE Professional framework, which then generated 20 complete lessons.

    The course looked like this:

    • Module 1: Reporting project updates
    • Module 2: Supply chain and logistics vocabulary
    • Module 3: Interpreting internal communications
    • Module 4: Coordination and problem-solving scenarios
    • Module 5: Safety presentation with feedback rubric

    From start to finish, the course took under an hour to build. It was tailored to his actual workday. His teacher later reported that his communication had become noticeably clearer and more confident.

    This was not a one-off. We have now repeated this flow for dozens of learners in different industries, each time mapping everything back to GSE ranges and skill targets.

    Why it works: AI + GSE = The right kind of structure

    AI helps us move fast. But the GSE gives us the structure to stay aligned.

    Without it, we’re just generating content. With it, we’re creating instruction that is:

    • Measurable and appropriate for the learner’s level
    • Easy for teachers to deliver
    • Consistent and scalable across programs

    The GSE gives us a shared language for goals, outcomes and progress. That is what keeps it pedagogically sound.

    Final thought

    A year ago, I wouldn’t have believed we could design a 20-lesson course in under an hour that actually delivers results. But now it’s just part of the workflow.

    AI doesn’t replace teaching. It enhances it. And when paired with the GSE, it gives us a way to meet learner needs with speed, clarity, and purpose. It’s not just an upgrade. It’s what’s next.