Posts Tagged ‘spaced repetition’

ltsigIt’s hype time again. Spurred on, no doubt, by the current spate of books and articles  about AIED (artificial intelligence in education), the IATEFL Learning Technologies SIG is organising an online event on the topic in November of this year. Currently, the most visible online references to AI in language learning are related to Glossika , basically a language learning system that uses spaced repetition, whose marketing department has realised that references to AI might help sell the product. GlossikaThey’re not alone – see, for example, Knowble which I reviewed earlier this year .

In the wider world of education, where AI has made greater inroads than in language teaching, every day brings more stuff: How artificial intelligence is changing teaching , 32 Ways AI is Improving Education , How artificial intelligence could help teachers do a better job , etc., etc. There’s a full-length book by Anthony Seldon, The Fourth Education Revolution: will artificial intelligence liberate or infantilise humanity? (2018, University of Buckingham Press) – one of the most poorly researched and badly edited books on education I’ve ever read, although that won’t stop it selling – and, no surprises here, there’s a Pearson commissioned report called Intelligence Unleashed: An argument for AI in Education (2016) which is available free.

Common to all these publications is the claim that AI will radically change education. When it comes to language teaching, a similar claim has been made by Donald Clark (described by Anthony Seldon as an education guru but perhaps best-known to many in ELT for his demolition of Sugata Mitra). In 2017, Clark wrote a blog post for Cambridge English (now unavailable) entitled How AI will reboot language learning, and a more recent version of this post, called AI has and will change language learning forever (sic) is available on Clark’s own blog. Given the history of the failure of education predictions, Clark is making bold claims. Thomas Edison (1922) believed that movies would revolutionize education. Radios were similarly hyped in the 1940s and in the 1960s it was the turn of TV. In the 1980s, Seymour Papert predicted the end of schools – ‘the computer will blow up the school’, he wrote. Twenty years later, we had the interactive possibilities of Web 2.0. As each technology failed to deliver on the hype, a new generation of enthusiasts found something else to make predictions about.

But is Donald Clark onto something? Developments in AI and computational linguistics have recently resulted in enormous progress in machine translation. Impressive advances in automatic speech recognition and generation, coupled with the power that can be packed into a handheld device, mean that we can expect some re-evaluation of the value of learning another language. Stephen Heppell, a specialist at Bournemouth University in the use of ICT in Education, has said: ‘Simultaneous translation is coming, making language teachers redundant. Modern languages teaching in future may be more about navigating cultural differences’ (quoted by Seldon, p.263). Well, maybe, but this is not Clark’s main interest.

Less a matter of opinion and much closer to the present day is the issue of assessment. AI is becoming ubiquitous in language testing. Cambridge, Pearson, TELC, Babbel and Duolingo are all using or exploring AI in their testing software, and we can expect to see this increase. Current, paper-based systems of testing subject knowledge are, according to Rosemary Luckin and Kristen Weatherby, outdated, ineffective, time-consuming, the cause of great anxiety and can easily be automated (Luckin, R. & Weatherby, K. 2018. ‘Learning analytics, artificial intelligence and the process of assessment’ in Luckin, R. (ed.) Enhancing Learning and Teaching with Technology, 2018. UCL Institute of Education Press, p.253). By capturing data of various kinds throughout a language learner’s course of study and by using AI to analyse learning development, continuous formative assessment becomes possible in ways that were previously unimaginable. ‘Assessment for Learning (AfL)’ or ‘Learning Oriented Assessment (LOA)’ are two terms used by Cambridge English to refer to the potential that AI offers which is described by Luckin (who is also one of the authors of the Pearson paper mentioned earlier). In practical terms, albeit in a still very limited way, this can be seen in the CUP course ‘Empower’, which combines CUP course content with validated LOA from Cambridge Assessment English.

Will this reboot or revolutionise language teaching? Probably not and here’s why. AIED systems need to operate with what is called a ‘domain knowledge model’. This specifies what is to be learnt and includes an analysis of the steps that must be taken to reach that learning goal. Some subjects (especially STEM subjects) ‘lend themselves much more readily to having their domains represented in ways that can be automatically reasoned about’ (du Boulay, D. et al., 2018. ‘Artificial intelligences and big data technologies to close the achievement gap’ in Luckin, R. (ed.) Enhancing Learning and Teaching with Technology, 2018. UCL Institute of Education Press, p.258). This is why most AIED systems have been built to teach these areas. Language are rather different. We simply do not have a domain knowledge model, except perhaps for the very lowest levels of language learning (and even that is highly questionable). Language learning is probably not, or not primarily, about acquiring subject knowledge. Debate still rages about the relationship between explicit language knowledge and language competence. AI-driven formative assessment will likely focus most on explicit language knowledge, as does most current language teaching. This will not reboot or revolutionise anything. It will more likely reinforce what is already happening: a model of language learning that assumes there is a strong interface between explicit knowledge and language competence. It is not a model that is shared by most SLA researchers.

So, one thing that AI can do (and is doing) for language learning is to improve the algorithms that determine the way that grammar and vocabulary are presented to individual learners in online programs. AI-optimised delivery of ‘English Grammar in Use’ may lead to some learning gains, but they are unlikely to be significant. It is not, in any case, what language learners need.

AI, Donald Clark suggests, can offer personalised learning. Precisely what kind of personalised learning this might be, and whether or not this is a good thing, remains unclear. A 2015 report funded by the Gates Foundation found that we currently lack evidence about the effectiveness of personalised learning. We do not know which aspects of personalised learning (learner autonomy, individualised learning pathways and instructional approaches, etc.) or which combinations of these will lead to gains in language learning. The complexity of the issues means that we may never have a satisfactory explanation. You can read my own exploration of the problems of personalised learning starting here .

What’s left? Clark suggests that chatbots are one area with ‘huge potential’. I beg to differ and I explained my reasons eighteen months ago . Chatbots work fine in very specific domains. As Clark says, they can be used for ‘controlled practice’, but ‘controlled practice’ means practice of specific language knowledge, the practice of limited conversational routines, for example. It could certainly be useful, but more than that? Taking things a stage further, Clark then suggests more holistic speaking and listening practice with Amazon Echo, Alexa or Google Home. If and when the day comes that we have general, as opposed to domain-specific, AI, chatting with one of these tools would open up vast new possibilities. Unfortunately, general AI does not exist, and until then Alexa and co will remain a poor substitute for human-human interaction (which is readily available online, anyway). Incidentally, AI could be used to form groups of online language learners to carry out communicative tasks – ‘the aim might be to design a grouping of students all at a similar cognitive level and of similar interests, or one where the participants bring different but complementary knowledge and skills’ (Luckin, R., Holmes, W., Griffiths, M. & Forceir, L.B. 2016. Intelligence Unleashed: An argument for AI in Education. London: Pearson, p.26).

Predictions about the impact of technology on education have a tendency to be made by people with a vested interest in the technologies. Edison was a businessman who had invested heavily in motion pictures. Donald Clark is an edtech entrepreneur whose company, Wildfire, uses AI in online learning programs. Stephen Heppell is executive chairman of LP+ who are currently developing a Chinese language learning community for 20 million Chinese school students. The reporting of AIED is almost invariably in websites that are paid for, in one way or another, by edtech companies. Predictions need, therefore, to be treated sceptically. Indeed, the safest prediction we can make about hyped educational technologies is that inflated expectations will be followed by disillusionment, before the technology finds a smaller niche.



MosaLingua  (with the obligatory capital letter in the middle) is a vocabulary app, available for iOS and Android. There are packages for a number of languages and English variations include general English, business English, vocabulary for TOEFL and vocabulary for TOEIC. The company follows the freemium model, with free ‘Lite’ versions and fuller content selling for €4.99. I tried the ‘Lite’ general English app, opting for French as my first language. Since the app is translation-based, you need to have one of the language pairings that are on offer (the other languages are currently Italian, Spanish, Portuguese and German).Mosalingua

The app I looked at is basically a phrase book with spaced repetition. Even though this particular app was general English, it appeared to be geared towards the casual business traveller. It uses the same algorithm as Anki, and users are taken through a sequence of (1) listening to an audio recording of the target item (word or phrase) along with the possibility of comparing a recording of yourself with the recording provided, (2) standard bilingual flashcard practice, (3) a practice stage where you are given the word or phrase in your own language and you have to unscramble words or letters to form the equivalent in English, and (4) a self-evaluation stage where users select from one of four options (“review”, “hard”, “good”, “perfect”) where the choice made will influence the re-presentation of the item within the spaced repetition.

In addition to these words and phrases, there are a number of dialogues where you (1) listen to the dialogue (‘without worrying about understanding everything’), (2) are re-exposed to the dialogue with English subtitles, (3) see it again with subtitles in your own language, (4) practise it with standard flashcards.

The developers seem to be proud of their Mosa Learning Method®: they’ve registered this as a trademark. At its heart is spaced repetition. This is supplemented by what they refer to as ‘Active Recall’, the notion that things are better memorised if the learner has to make some sort of cognitive effort, however minimal, in recalling the target items. The principle is, at least to me, unquestionable, but the realisation (unjumbling words or letters) becomes rather repetitive and, ultimately, tedious. Then, there is what they call ‘metacognition’. Again, this is informed by research, even if the realisation (self-evaluation of learning difficulty into four levels) is extremely limited. Then there is the Pareto principle  – the 80-20 rule. I couldn’t understand the explanation of what this has to do with the trademarked method. Here’s the MosaLingua explanation  – figure it out for yourself:

Did you know that the 100 most common words in English account for half of the written corpus?

Evidently, you shouldn’t quit after learning only 100 words. Instead, you should concentrate on the most frequently used words and you’ll make spectacular progress. What’s more, globish (global English) has shown that it’s possible to express yourself using only 1500 well-chosen words (which would take less than 3 months with only 10 minutes per day with MosaLingua). Once you’ve acquired this base, MosaLingua proposes specialized vocabulary suited to your needs (the application has over 3000 words).

Finally, there’s some stuff about motivation and learner psychology. This boils down to That’s why we offer free learning help via email, presenting the Web’s best resources, as well as tips through bonus material or the learning community on the MosaLingua blog. We’ll give you all the tools you need to develop your own personalized learning method that is adapted to your needs. Some of these tips are not at all bad, but there’s precious little in the way of gamification or other forms of easy motivation.

In short, it’s all reasonably respectable, despite the predilection for sciency language in the marketing blurb. But what really differentiates this product from Anki, as the founder, Samuel Michelot, points out is the content. Mosalingua has lists of vocabulary and phrases that were created by professors. The word ‘professors’ set my alarm bells ringing, and I wasn’t overly reassured when all I could find out about these ‘professors’ was the information about the MosaLingua team .professors

Despite what some people  claim, content is, actually, rather important when it comes to language learning. I’ll leave you with some examples of MosaLingua content (one dialogue and a selection of words / phrases organised by level) and you can make up your own mind.


Hi there, have a seat. What seems to be the problem?

I haven’t been feeling well since this morning. I have a very bad headache and I feel sick.

Do you feel tired? Have you had cold sweats?

Yes, I’m very tired and have had cold sweats. I have been feeling like that since this morning.

Have you been out in the sun?

Yes, this morning I was at the beach with my friends for a couple hours.

OK, it’s nothing serious. It’s just a bad case of sunstroke. You must drink lots of water and rest. I’ll prescribe you something for the headache and some after sun lotion.

Great, thank you, doctor. Bye.

You’re welcome. Bye.

Level 1: could you help me, I would like a …, I need to …, I don’t know, it’s okay, I (don’t) agree, do you speak English, to drink, to sleep, bank, I’m going to call the police

Level 2: I’m French, cheers, can you please repeat that, excuse me how can I get to …, map, turn left, corner, far (from), distance, thief, can you tell me where I can find …

Level 3: what does … mean, I’m learning English, excuse my English, famous, there, here, until, block, from, to turn, street corner, bar, nightclub, I have to be at the airport tomorrow morning

Level 4: OK, I’m thirty (years old), I love this country, how do you say …, what is it, it’s a bit like …, it’s a sort of …, it’s as small / big as …, is it far, where are we, where are we going, welcome, thanks but I can’t, how long have you been here, is this your first trip to England, take care, district / neighbourhood, in front (of)

Level 5: of course, can I ask you a question, you speak very well, I can’t find the way, David this is Julia, we meet at last, I would love to, where do you want to go, maybe another day, I’ll miss you, leave me alone, don’t touch me, what’s you email

Level 6: I’m here on a business trip, I came with some friends, where are the nightclubs, I feel like going to a bar, I can pick you up at your house, let’s go to see a movie, we had a lot of fun, come again, thanks for the invitation is an Israeli start-up which, in its own words, ‘is an innovative new learning solution that helps you learn a language from the open web’. Its platform ‘uses big-data paired with spaced repetition to help users bootstrap their way to fluency’. You can read more of this kind of adspeak at the blog  or the Wikipedia entry  which seems to have been written by someone from the company.

How does it work? First of all, state the language you want to study (currently there are 10 available) and the language you already speak (currently there are 18 available). Then, there are three possible starting points: insert a word which you want to study, click on a word in any web text or click on a word in one of the suggested reading texts. This then brings up a bilingual dictionary entry which, depending on the word, will offer a number of parts of speech and a number of translated word senses. Click on the appropriate part of speech and the appropriate word sense, and the item will be added to your personal word list. Once you have a handful of words in your word list, you can begin practising these words. Here there are two options. The first is a spaced repetition flashcard system. It presents the target word and 8 different translations in your own language, and you have to click on the correct option. Like most flashcard apps, spaced repetition software determines when and how often you will be re-presented with the item.

The second option is to read an authentic web text which contains one or more of your target items. The company calls this ‘digital language immersion, a method of employing a virtual learning environment to simulate the language learning environment’. The app ‘relies on a number of applied linguistics principles, including the Natural Approach and Krashen’s Input Hypothesis’, according to the Wikipedia entry. Apparently, the more you use the app, the more it knows about you as a learner, and the better able it is to select texts that are appropriate for you. As you read these texts, of course, you can click on more words and add them to your word list.

I tried out, logging on as a French speaker wanting to learn English, and clicking on words as the fancy took me. I soon had a selection of texts to read. Users are offered a topic menu which consisted of the following: arts, business, education, entertainment, food, weird, beginners, green, health, living, news, politics, psychology, religion, science, sports, style. The sources are varied and not at all bad – Christian Science Monitor, The Grauniad, Huffington Post, Time, for example –and there are many very recent articles. Some texts were interesting; others seemed very niche. I began clicking on more words that I thought would be interesting to explore and here my problems began.

I quickly discovered that the system could only deal with single words, so phrasal verbs were off limits. One text I looked at had the phrasal verb ‘ripping off’, and although I could get translations for ‘ripping’ and ‘off’, this was obviously not terribly helpful. Learners who don’t know the phrasal verb ‘ripped off’ do not necessarily know that it is a phrasal verb, so the translations offered for the two parts of the verb are worse than unhelpful; they are actually misleading. Proper nouns were also a problem, although some of the more common ones were recognised. But the system failed to recognise many proper nouns for what they were, and offered me translations of homonymous nouns. new_word_added_'ripping_off' With some words (e.g. ‘stablemate’), the dictionary offered only one translation (in this case, the literal translation), but not the translation (the much more common idiomatic one) that was needed in the context in which I came across the word. With others (e.g. ‘pertain’), I was offered a list of translations which included the one that was appropriate in the context, but, unfortunately, this is the French word ‘porter’, which has so many possible meanings that, if you genuinely didn’t know the word, you would be none the wiser.

Once you’ve clicked on an appropriate part of speech and translation (if you can find one), the dictionary look-up function offers both photos and example sentences. Here again there were problems. I’d clicked on the verb ‘pan’ which I’d encountered in the context of a critic panning a book they’d read. I was able to select an appropriate translation, but when I got to the photos, I was offered only multiple pictures of frying pans. There were no example sentences for my meaning of ‘pan’: instead, I was offered multiple sentences about cooking pans, and one about Peter Pan. In other cases, the example sentences were either unhelpful (e.g. the example for ‘deal’ was ‘I deal with that’) or bizarre (e.g. the example sentence for ‘deemed’ was ‘The boy deemed that he cheated in the examination’). For some words, there were no example sentences at all.

Primed in this way, I was intrigued to see how the system would deal with the phrase ‘heaving bosoms’ which came up in one text. ‘Heaving bosoms’ is an interesting case. It’s a strong collocation, and, statistically, ‘heaving bosoms’ plural are much more frequent than ‘a heaving bosom’ singular. ‘Heaving’, as an adjective, only really collocates with ‘bosoms’. You don’t find ‘heaving’ collocating with any of the synonyms for ‘bosoms’. The phrase is also heavily connoted, strongly associated with romance novels, and often used with humorous intent. Finally, there is also a problem of usage with ‘bosom’ / ‘bosoms’: men or women, one or two – all in all, it’s a tricky word. was no help at all. There was no dictionary entry for an adjectival ‘heaving’, and the translations for the verb ‘heave’ were amusing, but less than appropriate. As for ‘bosom’, there were appropriate translations (‘sein’ and ‘poitrine’), but absolutely no help with how the word is actually used. Example sentences, which are clearly not tagged to the translation which has been chosen, included ‘Or whether he shall die in the bosom of his family or neglected and despised in a foreign land’ and ‘Can a man take fire in his bosom, and his clothes not be burned?’ has a number of problems. First off, its software hinges on a dictionary (it’s a Babylon dictionary) which can only deal with single words, is incomplete, and does not deal with collocation, connotation, style or register. As such, it can only be of limited value for receptive use, and of no value whatsoever for productive use. Secondly, the web corpus that it is using simply isn’t big enough. Thirdly, it doesn’t seem to have any Natural Language Processing tool which could enable it to deal with meanings in context. It can’t disambiguate words automatically. Such software does now exist, and desperately needs it.

Unfortunately, there are other problems, too. The flashcard practice is very repetitive and soon becomes boring. With eight translations to choose from, you have to scroll down the page to see them all. But there’s a timer mechanism, and I frequently timed out before being able to select the correct translation (partly because words are presented with no context, so you have to remember the meaning which you clicked in an earlier study session). The texts do not seem to be graded for level. There is no indication of word frequency or word sense frequency. There is just one gamification element (a score card), but there is no indication of how scores are achieved. Last, but certainly not least, the system is buggy. My word list disappeared into the cloud earlier today, and has not been seen since.

I think it’s a pity that is not better. The idea behind it is good – even if the references to Krashen are a little unfortunate. The company says that they have raised $800,000 in funding, but with their freemium model they’ll be desperately needing more, and they’ve gone to market too soon. One reviewer, Language Surfer,  wrote a withering review of’s Arabic program (‘it will do more harm than good to the Arabic student’), and Brendan Wightman, commenting at eltjam,  called it ‘dull as dish water, […] still very crude, limited and replete with multiple flaws’. But, at least, it’s free.