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. 

app English International Certificate (PEIC)

app 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 app

  • A group of friends backpacking outdoors smiling and embracing eachother

    What are the most spoken languages in the world?

    By Charlotte Guest
    Reading time: 5 minutes

    Have you ever wondered which world languages are spoken by the largest number of people globally? Whether you’re a language enthusiast or someone looking to learn a new language, understanding the most spoken languages around the world can be incredibly insightful. In this blog post, we’ll explore the top languages by number of speakers, shedding light on languages with the most native speakers and widely spoken languages globally.

    Introduction to spoken languages

    Spoken languages are a vital part of human communication, culture and identity. With over 7,000 languages spoken worldwide, each language has its unique characteristics, nuances and significance. Understanding the most spoken languages globally provides valuable insights into geopolitics, economics and social dynamics. In this article, we will explore the top languages spoken in the world, their distribution and use.

    Why knowing the most spoken languages matters

    Knowing which languages are most popular worldwide can influence your language learning decisions. Enhancing your language skills in these widely spoken languages can significantly boost your communication abilities and cultural understanding. It can open up opportunities for travel, business and cultural exchange. Additionally, understanding global language popularity can give you a broader perspective of the world’s linguistic diversity.

    Criteria for measuring language popularity

    Measuring language popularity is a complex task that involves various factors, including the number of native speakers, global influence, and use as a second or foreign language. The criteria for measuring language popularity include:

    • Number of native speakers: This refers to the number of people who speak a language as their first or native language. Languages with the highest number of native speakers often have a significant cultural and historical impact.

    • Global influence: This measures the extent to which a language is used in international communication, business, science and diplomacy. Languages with a broad global influence are often used as lingua francas in various regions.

    • Use as a second or foreign language: This considers the number of people who speak a language as a second language or foreign language. Languages that are widely taught and learned around the world tend to have a larger speaking population.

    By considering these criteria, we can better understand why certain languages are more prominent and widely spoken globally.

    Top 10 most spoken languages in the world

    Here’s a closer look at the ten most spoken languages by number of speakers:

    When evaluating these languages, it's important to consider not just the number of native speakers but also the total number of language speakers, including those who speak it as a second language.

    1. English

    Speakers: Approximately 1.5 billion

    Native speakers: Around 360 million

    Regions: Widely spoken in the Americas, Europe, Africa, Asia and Oceania.

    Highlights: English is the most widely spoken language worldwide when combining native and non-native speakers. It's the primary language in countries like the United States, the United Kingdom, Canada and Australia. English is the dominant language in international business, science and technology.

    2. Mandarin Chinese

    Speakers: Over 1.1 billion

    Native speakers: About 920 million

    Regions: Mainly in China, Taiwan and Singapore

    Highlights: Mandarin is the language with the largest number of native speakers. It's one of the six official languages of the United Nations and has a significant cultural and historical importance.

    3. Hindi

    Speakers: Around 600 million

    Native speakers: Approximately 341 million

    Regions: Predominantly in India and Nepal

    Highlights: Hindi is predominantly spoken in India and Nepal, with approximately 341 million native speakers. It is one of the official languages of India and is spoken by a large portion of the Indian population. It has numerous dialects and is written in the Devanagari script.

    4. Spanish

    Speakers: Approximately 560 million

    Native speakers: About 460 million

    Regions: Spain, Latin America and parts of the United States

    Highlights: Spanish is the official language in 21 countries and is widely spoken in the Americas. In many of these countries, Spanish serves as the national language, playing a crucial role in government, education and media. It’s known for its rich literature and cultural heritage.

    5. French

    Speakers: Around 280 million

    Native speakers: About 77 million

    Regions: France, parts of Africa, Canada, Belgium and Switzerland

    Highlights: French is another of the six official languages of the United Nations. It's widely used in international diplomacy and has a significant number of speakers in Africa due to France's colonial history.

    6. Arabic

    Speakers: Approximately 270 million

    Native speakers: Around 310 million

    Regions: Middle East and North Africa

    Highlights: Arabic is a central Semitic language that is the liturgical language of Islam. It has many dialects, with Modern Standard Arabic being used in formal settings and media. Arabic has numerous spoken forms, with significant variations in dialects across different regions.

    7. Bengali

    Speakers: Around 265 million

    Native speakers: About 230 million

    Regions: Bangladesh and parts of India

    Highlights: Bengali is the official language of Bangladesh and the second most spoken language in India. Alongside other languages like Hindi and Urdu, Bengali plays a crucial role in the cultural and linguistic landscape of the region. It’s known for its rich literary tradition.

    8. Portuguese

    Speakers: Approximately 220 million

    Native speakers: Around 220 million

    Regions: Brazil, Portugal and parts of Africa

    Highlights: Portuguese is mainly spoken in Brazil, which is the largest Portuguese-speaking country. It has a growing number of speakers in Africa.

    9. Russian

    Speakers: Around 258 million

    Native speakers: Approximately 154 million

    Regions: Russia, Eastern Europe and Central Asia

    Highlights: Russian is one of the six official languages of the United Nations and is widely spoken in the former Soviet Union countries.

    10. Japanese

    Speakers: Approximately 128 million

    Native speakers: Around 128 million

    Regions: Japan

    Highlights: Japanese is predominantly spoken in Japan and is known for its three writing systems—Hiragana, Katakana and Kanji. It has a rich cultural history and is influential in technology and entertainment.

    Conclusion

    Understanding the most spoken languages in the world can provide valuable insights for language learners. Developing strong language skills in these world languages can open up numerous opportunities for travel, business and cultural exchange. Whether you’re looking to enhance your travel experiences, broaden your cultural horizons, or improve your career prospects, learning one of these widely spoken languages could be a significant advantage.

    Ready to start your language learning journey? Learn a new language with Mondly by app.

  • Woman working in front of a laptop writing something down and smiling

    Learning a language while working full-time

    By Charlotte Guest
    Reading time: 4 minutes

    Mastering a new language can be a game-changer for your career. Whether it's for expanding your professional network, exploring new job opportunities, or simply enhancing your cognitive skills, learning a language is an invaluable investment. But how can you juggle language learning with a demanding full-time job? Here are some practical tips designed for busy professionals.

    1. Set clear goals

    Before you start, it's crucial to set clear, achievable goals. Whether you aim to hold basic conversations, read professional documents, or become fluent, having a specific target will keep you motivated and focused.

    2. Integrate learning into your daily routine

    Finding time to study can be challenging, but integrating language learning into your daily routine can make it more manageable:

    • Commute time: Use your commute to listen to language podcasts or audiobooks.
    • Lunch breaks: Dedicate 15-20 minutes of your lunch break to review vocabulary or grammar.
    • Evening wind-down: Spend 10 minutes before bed practicing speaking or writing.

    3. Use online resources

    Modern technology provides a plethora of tools to help you learn a new language without disrupting your schedule:

    • Language learning apps: Apps like Mondly by app allow you to practice during your commute or lunch break.
    • Podcasts and audiobooks: Listen to language lessons during your commute or workout.
    • Online courses: Many websites offer structured courses that you can complete at your own pace.

    4. Stay motivated

    Staying motivated is crucial to your success. Celebrate your progress, no matter how small, and remind yourself of the benefits of being multilingual:

    • Track your progress: Keep a journal of your language learning milestones and achievements.
    • Find a study buddy: Partner with a colleague or friend who is also learning the language to keep each other accountable.
    • Reward yourself: Treat yourself when you reach your language learning goals.

    5. Explore company resources

    Some companies offer resources or discounted access for learning. It's always worthwhile to check if your employer provides:

    • Language classes: On-site or online language classes.
    • Learning platforms: Subscriptions to language learning platforms.
    • Education reimbursement: Financial assistance for language courses as part of professional development.

    6. Use your work environment

    If your workplace has international colleagues, take advantage of this opportunity to practice. Try to speak with them in their first language or ask for help with pronunciation and vocabulary. Not only will this provide real-world practice, but it will also strengthen your professional relationships.

    7. Be consistent and patient

    Consistency is key when learning a new language:

    • Daily practice: Even 10-15 minutes a day can lead to significant progress over time.
    • Patience: Language learning is a gradual process. Celebrate small milestones and remain patient with your progress.

    Balancing a full-time job with language learning is no small feat, but it's entirely possible with the right strategies. By setting clear goals, integrating learning into your routine, leveraging technology, practicing consistently, engaging with native speakers, making learning fun and staying motivated, you can achieve fluency without sacrificing your professional responsibilities. Ready to start your language learning journey? Take the first step today and open a world of new opportunities.

  • A man looking at a openlaptop with a pen in hand, smiling at the laptop

    7 myths about learning a new language debunked

    By Charlotte Guest
    Reading time: 3 minutes

    Learning a new language can be an incredibly rewarding experience, opening doors to new cultures, enhancing career opportunities and providing cognitive benefits. However, many myths about language learning can discourage potential learners or lead them astray. Today, we're debunking seven common language learning myths to help you on your linguistic journey.

    Myth 1: "You need to start young to be fluent"

    Truth:

    It's never too late to learn a new language. While children may pick up accents and intonation more easily, adults often have the advantage of better-developed cognitive skills and life experiences that can aid in understanding complex grammar and vocabulary. Numerous studies have shown that adults can achieve fluency with dedication and the right learning strategies.

    Myth 2: "You have to live in a country to learn the language"

    Truth:

    Thanks to technology, you can immerse yourself in a new language without leaving your home. Tools like language learning apps, online courses, virtual tutors and even social media can provide ample opportunities for practice and immersion. Living in a country where the language is spoken can be beneficial, but it is not a necessity.

    Myth 3: "You must be naturally gifted to learn languages"

    Truth:

    Language learning is less about innate talent and more about consistent practice and effective methods. Anyone can learn a new language with the right mindset and resources. Persistence, motivation and using varied learning techniques can significantly enhance your ability to learn.

    Myth 4: "It's all about memorizing vocabulary"

    Truth:

    While vocabulary is essential, language learning involves much more than rote memorization. Understanding grammar, practicing speaking and listening, and getting a feel for cultural nuances are equally important. Engaging in conversations, reading and writing in the language can make the learning process more holistic and enjoyable.

    Myth 5: "You can't learn multiple languages at once"

    Truth:

    Learning multiple languages simultaneously is possible, though it does require careful planning and organization. The key is to manage your time effectively and ensure that you are not overwhelming yourself. Using different methods and tools for each language can help keep them distinct in your mind.

    Myth 6: "Watching movies and listening to music doesn't count as learning"

    Truth:

    Consuming media in your target language can be an excellent way to improve your listening skills and cultural understanding. Movies, TV shows, music and podcasts expose you to natural language usage, slang and colloquial expressions that textbooks may not cover. It's a fun and engaging complementary method to more formal study.

    Myth 7: "If you can't speak perfectly, don't try"

    Truth:

    Perfectionism can be a significant barrier to language learning. Making mistakes is a natural part of the learning process. The more you practice speaking, the more confident and proficient you'll become. Focus on communication rather than perfection, and don't be afraid to make errors—they're your stepping stones to fluency.

    Conclusion

    By debunking these myths, we hope to encourage more people to take up the challenge of learning a new language. Remember, the most important factors are consistency, practice and a willingness to learn from mistakes.

    Ready to tackle a new language? Start today and immerse yourself in the endless possibilities that come with being multilingual. Explore the benefits with our post, 'Being bilingual can help keep your brain in good condition'.