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.
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 . 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 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.
At ɫèAV, 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 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.
ɫèAV 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?'.
English is one of the most widely-spoken languages in the world, but how much do you know about the language? Here are 11 facts about Englishthat you might not know.
Students all over the globe learn English for many reasons. Some of these motivations may come from the students themselves – perhaps they are learning because they are travelling to an English-speaking area, or they want to be able to converse with English-speaking friends and colleagues. Other reasons for learning could include meeting school requirements, studying abroad, or progressing their careers.
As well as different reasons to learn English, there are also different goals. Many students are still focused on becoming fluent in English, and we are seeing an increase in people who want to learn the language for specific reasons. For example, immersing themselves in a particular culture or simply being able to order from a menu while travelling abroad.
Teachers are focusing on these personal needs to help students achieve their actual goals. It’s likely you’ve already spoken to your students about why they want to learn English. Understanding this is important as different motivations can influence a student’s attitude towards learning the language – and it may be necessary for you to adapt your teaching strategies for different groups of learners.
Let’s meet some different groups of students, learn a little more about their motivations and explore whether different motivations alter how students learn English. You may recognise some of these learners in your classes.
These students are learning English for pleasure or personal reasons. It might be because of travel, social or family reasons or perhaps because a better grasp of English might assist them with their careers. There are also adult learners who could be learning English as an immigration requirement.
For example, 23-year-old Alice decided to learn English so she could meet people and have more meaningful interactions with her English-speaking neighbours. She says: “I was very shy and not very confident in speaking to people, but learning English helped me connect with others and meet new people. I have changed a lot.”
A motivation like Alice’s requires strong teacher support and peer motivation woven into structured learning. Alice can set her goals and with the GSE Learning Objectives map out what she needs to do to achieve them. Teacher encouragement and personal support – and easy access to digital coursework, a social community of others all learning English, and small classes that emphasise conversation – keep people like Alice engaged and motivated to achieve her language goals. “I cannot do it without them”, she says.
These learners are typically in a more formal type of English programme and are learning the language to achieve specific career milestones, such as a promotion. Their employer might even be paying for their learning or they might be reimbursed for the cost of their lessons.
Vincenzo is 33 and works as a Product Manager in Milan for an international organization with offices around the world. He says: “I asked to take English classes as part of my professional development. My company chose an English provider and gave me a choice of group or one-to-one classes. I chose one-to-one classes as I’m easily distracted.”
Professional learners like Vincenzo succeed using a blended learning model of learning in class and at home that they can tailor around their lives. They have a strong motivation to succeed – that’s why learning at home works for them – but step-by-step progress provided by the GSE Learning Objectives is also important to keep this motivation alive. “I met with my teacher once a week where we would work on mistakes I would make while speaking English. He would also give me extra practice materials, like interesting games and videos to listen to in my own time, to help me really get a better understanding of the language,” Vincenzo says.
Learning English is a requirement for many school programmes and students will continue this at college or university. Many of these students will be learning English with a formal course that offers practice tests for high-stakes exams.
Seventeen-year-old Subra is from Malaysia and learns English at school. Some of her family live in Australia and she is considering studying abroad to attend a University that specializes in health care. When she was young, she learned in a traditional classroom backed with tests that helped her see how she was progressing. Now she uses technology, such as her Android Huawei phone to practise her English but still needs the validation of regular testing to know she is on track.
Subrasays: “I am used to studying for tests as I prepared hard for exams to get into middle school and senior school, which was totally determined by test results.”
Academic learners like Subra need to see demonstrable results to help them stay motivated and guide them to the level of English they need to achieve to get the required score on high-stakes tests. With the clear GSE Learning Objectives and a placement test, academic learners can map out where they are right now and where they need to be in order to reach their academic goals. These learners need encouragement and validation of their progress from their teachers to help keep them on track.
Understanding student motivations will help you teach to their specific needs, thus helping them to stay focused and motivated in achieving their goals.
Kirsty Murray taught English for a year at a collège (the French equivalent of a secondary school) in Villers-Cotterêts: a town in the north of France known for being the birthplace of Alexandre Dumas. She taught mixed-ability groups of 11- to 16-year-olds, with classes ranging in size from 10 to 35 students. Here, she shares the five lessons she learned from the experience.
