Explaining computerized English testing in plain English

app 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 app’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.

app 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 app’s Ordinate technology

The spoken portion of PTE Academic is automatically scored using app’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 app’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 app

  • A group of friends sat outside smiling and talking

    Lesser-known differences between British and American English

    Por Heath Pulliam
    Reading time: 5 minutes

    Heath Pulliam is an independent education writer with a focus on the language learning space. He’s taught English in South Korea and various subjects in the United States to a variety of ages. He’s also a language learning enthusiast and studies Spanish in his free time.

    British and American English are two well-known varieties of the English language. While the accent is often the first difference people notice, there are also subtle distinctions in vocabulary, grammar and even style. Many know about how Brits say boot and lift, while Americans would say trunk and elevator, but what about a few lesser-known differences?

    Here, we take a look at a few of the more obscure differences between British English (BrE) and American English (AmE).

    Note: British English is underlined and American English isitalicized.

    1.Footballerandfootball player

    Along with the well-known difference of how in the U.S., football refers to American football, while football in Britain is what Americans like me call soccer, Americans also use player after the sport to denote someone who plays the sport. In British English, the sport with an added -er suffix is more common, like footballer and cricketer, not football player or cricket player.

    This is not universal, though. For some sports, the -er suffix is used in both dialects. Both Brits and Americans use the term golfer, not golf player. There are also sports where the -er suffix is never used, like for tennis, cycling and gymnastics. Nobody says tenniser, tennis player is used instead.

    People who cycle are cyclists and people who do gymnastics are gymnasts. Sometimes, badminton players are even called badmintonists. Overall, there aren’t really any concrete rules for what to call each player of a sport. Each sport has its own way of calling someone who participates in that sport.

    2.I dzܱ’t care lessandI could care less

    The American version (I could care less) means the same thing. Although technically incorrect, it is still widely used in North America as an idiom and will be interpreted as not caring at all about something. Although popular, both variations can be heard in North America. Regardless, miscommunications do happen surrounding this phrase.

    “I could care less about who Harry Styles is dating right now.”

    “Oh, I didn’t know you were interested in tabloid news.”

    “I’m not! I just said I didn’t care about it.”

    “No, you said that you could care less, meaning that it is possible for you to care less about who he’s dating.”

    “Ugh! What I mean is that I dzܱ’t care less. Happy?”

    3. American simplification

    Both British and American dialects are filled with many minuscule differences in spelling and phrasing. For example, the words plough (BrE) and plow (AmE) mean the same thing, but are spelled differently.

    When two words differ, American English generally favors the simpler, more phonetic spelling. Hey, there’s another one! Favour (BrE) and favor (AmE). It’s apparent in pairs like analyse (BrE) and analyze (AmE), and neighbour (BrE) and neighbor (AmE).

    Many of these small spelling differences can be attributed to Noah Webster, author of Webster’s Dictionary, who sought to distinguish American from British English by simplifying many of the words.

    Some of his simplifications to American English are swapping the s for z, (specialised to specialized), dropping the u in words ending in our, (colour to color), and changing words ending in -tre to -ter (theatre to theater).

    4. Courgette and zucchini

    The history of this vegetable, whatever you may call it, tells us why zucchini is used in American English and courgette is used in British English. If you’ve studied languages, you can probably guess what country each name originated from. England was introduced to this cylinder-shaped vegetable in the 19th century by its French neighbors, while Americans were introduced to it in the early 20th century by the large influx of Italian immigrants.

    The word zucchini is something of a mistranslation from Italian, however. What Americans use (zucchini) is the plural masculine form of the proper Italian word, (zucchino).

    5.Anticlockwiseand counterclockwise

    These terms mean the same thing, the rotation against the way a clock runs. In British English, this movement would be called anticlockwise, and in the U.S., they use counterclockwise.The prefixesanti- andcounter- mean similar things.Anti- means against, andcounter- means contrary or opposite to.

    You should use antibacterial soap in order to stop the spread of germs.Buying cheap clothes that only last you a few months is counterproductive in the long term.

    Can you guess how they described this movement before the invention of clocks with hands and circular faces? English speakers this long ago used sunwise. This direction at the time was considered auspicious and the opposite of the other direction.

    6.Haveand take

    Have and take are used often before nouns like shower, break, bath, rest and nap.In the U.S., peopletakeshowers andtakenaps, while in the U.K., peoplehaveshowers andhavenaps. Another example of this is how Americanstakea swim and Britshavea swim. These are called delexical verbs and we use them all the time in English, both British and American.

    Although often different, both groups of English speakers have arguments, make decisions and take breaks.

    7.Quite

    This word is spelled the same in both American and British English, but means something different. In the U.S.,quiteis typically used as an intensifier, like the wordvery.In the U.K., it’s normally used as a mitigator, like the wordsomewhat.

    It can also mean completely if it modifies certain adjectives. (e.g., It’s quite impossible to learn a language in one month.)

    American English: That Mexican food we had yesterday was quite spicy.

    Translation: That Mexican food we had yesterday was very spicy.

    In British English, quite means something more on the lines of kind of, or a bit.

    British English: Thank you for the meal, it was quite good.

    Translation: Thank you for the meal, it was somewhat good.

    8. Clothing differences

    The category of clothes is one of the richest, with differences between the two English variants.How about those pants that people used to only wear at the gym and around the house, but now wear them everywhere?

    Brits call themtracksuit bottomsand Americans call themsweatpants. What about a lightweight jacket that protects from wind and rain?Brits might call this ananorak(derived from the Greenlandic word), but Americans would call it awindbreaker. Both variants also useraincoatfor this article of clothing.

    9.Torchandflashlight

    As an American, I’ve been confused before when coming across the word torch while reading the work of an English author.

    To Americans, a torch is a piece of wood with the end lit on fire for light.What Brits are referring to when they use the wordtorchis aflashlight (AmE), a small, battery-run electric lamp.

    10.’t and don’t need to

    Ah, the English contraction. Many English learners don’t particularly love learning these, but they are an essential and everyday part of the language. ’t, however, is one that I don’t think I’ve ever heard another American say.

    In the U.K., this contraction is fairly common. ’t, when separated, becomes need not.

    British English: “You needn’t come until Tuesday night.”

    Americans would say the relatively simpler don’t need to.

    American English: “You don’t need to come until Tuesday night.”

    Don’t be fooled into thinking British English has necessarily more difficult contractions than the U.S., though. Just come to the American South and prepare to hear famous (or infamous) contractions like y’all (you all) and ain’t (am not, is not, are not)!

    Conclusion

    There are hundreds of differences between British and American dialects, we’re only scratching the surface here.Some of these make more sense than others, but luckily, both Brits and Americans can usually understand the meaning of any English word through context.

    Some people would even say that Brits speak English while Americans speak American.Although each dialect from across the pond seems very different, they have far more similarities than differences.

  • Three business people stood together in a corridor smiling at eaching and talking

    What level of English do my employees need?

    Por Samantha Ball
    Reading time: 3 minutes

    Whether you're hiring new talent or upskilling your current team, understanding the level of English proficiency required for specific roles is crucial. In today's global business environment, effective communication is key to success, and that's where the Global Scale of English (GSE) comes into play.

  • Coworkers sat at a table together, talking and smiling

    Target employees’ English language upskilling with the GSE Job Profiles

    Por Samantha Ball
    Reading time: 4 minutes

    Staying ahead requires not just talent but the right talent. For HR professionals, ensuring that employees are equipped with the necessary skills is crucial for maintaining a competitive edge. Enter the GSE Job Profiles—a game-changing tool designed to facilitate role-targeted upskilling by mapping English language skills to specific job roles. This blog post will explore how HR teams can leverage this innovative tool to enhance workforce capabilities efficiently and effectively.

    The GSE Job Profiles utilizes app’s Global Scale of English and the Faethm by app skills ontology to provide a detailed analysis of the language requirements for nearly 1,400 job roles. This precise mapping allows HR professionals to make informed talent management decisions, including hiring, training and development, and ensuring that employees are adequately prepared for their roles now and in the future.