Archive for March, 2018

It’s international ELT conference season again, with TESOL Chicago having just come to a close and IATEFL Brighton soon to start. I decided to take a look at how the subject of personalized learning will be covered at the second of these. Taking the conference programme , I trawled through looking for references to my topic.

Jing_word_cloudMy first question was: how do conference presenters feel about personalised learning? One way of finding out is by looking at the adjectives that are found in close proximity. This is what you get.

The overall enthusiasm is even clearer when the contexts are looked at more closely. Here are a few examples:

  • inspiring assessment, personalising learning
  • personalised training can contribute to professionalism and […] spark ideas for teacher trainers
  • a personalised educational experience that ultimately improves learner outcomes
  • personalised teacher development: is it achievable?

Particularly striking is the complete absence of anything that suggests that personalized learning might not be a ‘good thing’. The assumption throughout is that personalized learning is desirable and the only question that is asked is how it can be achieved. Unfortunately (and however much we might like to believe that it is a ‘good thing’), there is a serious lack of research evidence which demonstrates that this is the case. I have written about this here and here and here . For a useful summary of the current situation, see Benjamin Riley’s article where he writes that ‘it seems wise to ask what evidence we presently have that personalized learning works. Answer: Virtually none. One remarkable aspect of the personalized-learning craze is how quickly the concept has spread despite the almost total absence of rigorous research in support of it, at least thus far.’

Given that personalized learning can mean so many things and given the fact that people do not have space to define their terms in their conference abstracts, it is interesting to see what other aspects of language learning / teaching it is associated with. The four main areas are as follows (in alphabetical order):

  • assessment (especially formative assessment) / learning outcomes
  • continuous professional development
  • learner autonomy
  • technology / blended learning

The IATEFL TD SIG would appear to be one of the main promoters of personalized learning (or personalized teacher development) with a one-day pre-conference event entitled ‘Personalised teacher development – is it achievable?’ and a ‘showcase’ forum entitled ‘Forum on Effective & personalised: the holy grail of CPD’. Amusingly (but coincidentally, I suppose), the forum takes place in the ‘Cambridge room’ (see below).

I can understand why the SIG organisers may have chosen this focus. It’s something of a hot topic, and getting hotter. For example:

  • Cambridge University Press has identified personalization as one of the ‘six key principles of effective teacher development programmes’ and is offering tailor-made teacher development programmes for institutions.
  • NILE and Macmillan recently launched a partnership whose brief is to ‘curate personalised professional development with an appropriate mix of ‘formal’ and ‘informal’ learning delivered online, blended and face to face’.
  • Pearson has developed the Pearson’s Teacher Development Interactive (TDI) – ‘an interactive online course to train and certify teachers to deliver effective instruction in English as a foreign language […] You can complete each module on your own time, at your own pace from anywhere you have access to the internet.’

These examples do not, of course, provide any explanation for why personalized learning is a hot topic, but the answer to that is simple. Money. Billions and billions, and if you want a breakdown, have a look at the appendix of Monica Bulger’s report, ‘Personalized Learning: The Conversations We’re Not Having’ . Starting with Microsoft and the Gates Foundation plus Facebook and the Chan / Zuckerberg Foundation, dozens of venture philanthropists have thrown unimaginable sums of money at the idea of personalized learning. They have backed up their cash with powerful lobbying and their message has got through. Consent has been successfully manufactured.

PearsonOne of the most significant players in this field is Pearson, who have long been one of the most visible promoters of personalized learning (see the screen capture). At IATEFL, two of the ten conference abstracts which include the word ‘personalized’ are directly sponsored by Pearson. Pearson actually have ten presentations they have directly sponsored or are very closely associated with. Many of these do not refer to personalized learning in the abstract, but would presumably do so in the presentations themselves. There is, for example, a report on a professional development programme in Brazil using TDI (see above). There are two talks about the GSE, described as a tool ‘used to provide a personalised view of students’ language’. The marketing intent is clear: Pearson is to be associated with personalized learning (which is, in turn, associated with a variety of tech tools) – they even have a VP of data analytics, data science and personalized learning.

But the direct funding of the message is probably less important these days than the reinforcement, by those with no vested interests, of the set of beliefs, the ideology, which underpin the selling of personalized learning products. According to this script, personalized learning can promote creativity, empowerment, inclusiveness and preparedness for the real world of work. It sets itself up in opposition to lockstep and factory models of education, and sets learners free as consumers in a world of educational choice. It is a message with which it is hard for many of us to disagree.

manufacturing consentIt is also a marvellous example of propaganda, of the way that consent is manufactured. (If you haven’t read it yet, it’s probably time to read Herman and Chomsky’s ‘Manufacturing Consent: The Political Economy of the Mass Media’.) An excellent account of the way that consent for personalized learning has been manufactured can be found at Benjamin Doxtdator’s blog .

So, a hot topic it is, and its multiple inclusion in the conference programme will no doubt be welcomed by those who are selling ‘personalized’ products. It must be very satisfying to see how normalised the term has become, how it’s no longer necessary to spend too much on promoting the idea, how it’s so associated with technology, (formative) assessment, autonomy and teacher development … since others are doing it for you.


A personalized language learning programme that is worth its name needs to offer a wide variety of paths to accommodate the varying interests, priorities, levels and preferred approaches to learning of the users of the programme. For this to be possible, a huge quantity of learning material is needed (Iwata et al., 2011: 1): the preparation and curation of this material is extremely time-consuming and expensive (despite the pittance that is paid to writers and editors). It’s not surprising, then, that a growing amount of research is being devoted to the exploration of ways of automatically generating language learning material. One area that has attracted a lot of attention is the learning of vocabulary.

Memrise screenshot 2Many simple vocabulary learning tasks are relatively simple to generate automatically. These include matching tasks of various kinds, such as the matching of words or phrases to meanings (either in English or the L1), pictures or collocations, as in many flashcard apps. Doing it well is rather harder: the definitions or translations have to be good and appropriate for learners of the level, the pictures need to be appropriate. If, as is often the case, the lexical items have come from a text or form part of a group of some kind, sense disambiguation software will be needed to ensure that the right meaning is being practised. Anyone who has used flashcard apps knows that the major problem is usually the quality of the content (whether it has been automatically generated or written by someone).

A further challenge is the generation of distractors. In the example here (from Memrise), the distractors have been so badly generated as to render the task more or less a complete waste of time. Distractors must, in some way, be viable alternatives (Smith et al., 2010) but still clearly wrong. That means they should normally be the same part of speech and true cognates should be avoided. Research into the automatic generation of distractors is well-advanced (see, for instance, Kumar at al., 2015) with Smith et al (2010), for example, using a very large corpus and various functions of Sketch Engine (the most well-known corpus query tool) to find collocates and other distractors. Their TEDDCLOG (Testing English with Data-Driven CLOze Generation) system produced distractors that were deemed acceptable 91% of the time. Whilst impressive, there is still a long way to go before human editing / rewriting is no longer needed.

One area that has attracted attention is, of course, tests, and some tasks, such as those in TOEFL (see image). Susanti et al (2015, 2017) were able, given a target word, to automatically generate a reading passage from web sources along with questions of the TOEFL kind. However, only about half of them were considered good enough to be used in actual tests. Again, that is some way off avoiding human intervention altogether, but the automatically generated texts and questions can greatly facilitate the work of human item writers.

toefl task


Other tools that might be useful include the University of Nottingham AWL (Academic Word List) Gapmaker . This allows users to type or paste in a text, from which items from the AWL are extracted and replaced as a gap. See the example below. It would, presumably, not be too difficult, to combine this approach with automatic distractor generation and to create multiple choice tasks.


WordGapThere are a number of applications that offer the possibility of generating cloze tasks from texts selected by the user (learner or teacher). These have not always been designed with the language learner in mind but one that was is the Android app, WordGap (Knoop & Wilske, 2013). Described by its developers as a tool that ‘provides highly individualized exercises to support contextualized mobile vocabulary learning …. It matches the interests of the learner and increases the motivation to learn’. It may well do all that, but then again, perhaps not. As Knoop & Wilske acknowledge, it is only appropriate for adult, advanced learners and its value as a learning task is questionable. The target item that has been automatically selected is ‘novel’, a word that features in the list Oxford 2000 Keywords (as do all three distractors), and therefore ought to be well below the level of the users. Some people might find this fun, but, in terms of learning, they would probably be better off using an app that made instant look-up of words in the text possible.

More interesting, in my view, is TEDDCLOG (Smith et al., 2010), a system that, given a target learning item (here the focus is on collocations), trawls a large corpus to find the best sentence that illustrates it. ‘Good sentences’ were defined as those which were short (but not too short, or there is not enough useful context, begins with a capital letter and ends with a full stop, has a maximum of two commas; and otherwise contains only the 26 lowercase letters. It must be at a lexical and grammatical level that an intermediate level learner of English could be expected to understand. It must be well-formed and without too much superfluous material. All others were rejected. TEDDCLOG uses Sketch Engine’s GDEX function (Good Dictionary Example Extractor, Kilgarriff et al 2008) to do this.

My own interest in this area came about as a result of my work in the development of the Oxford Vocabulary Trainer . The app offers the possibility of studying both pre-determined lexical items (e.g. the vocabulary list of a coursebook that the learner is using) and free choice (any item could be activated and sent to a learning queue). In both cases, practice takes the form of sentences with the target item gapped. There are a range of hints and help options available to the learner, and feedback is both automatic and formative (i.e. if the supplied answer is not correct, hints are given to push the learner to do better on a second attempt). Leveraging some fairly heavy technology, we were able to achieve a fair amount of success in the automation of intelligent feedback, but what had, at first sight, seemed a lesser challenge – the generation of suitable ‘carrier sentences’, proved more difficult.

The sentences which ‘carry’ the gap should, ideally, be authentic: invented examples often ‘do not replicate the phraseology and collocational preferences of naturally-occurring text’ (Smith et al., 2010). The technology of corpus search tools should allow us to do a better job than human item writers. For that to be the case, we need not only good search tools but a good corpus … and some are better than others for the purposes of language learning. As Fenogenova & Kuzmenko (2016) discovered when using different corpora to automatically generate multiple choice vocabulary exercises, the British Academic Written English corpus (BAWE) was almost 50% more useful than the British National Corpus (BNC). In the development of the Oxford Vocabulary Trainer, we thought we had the best corpus we could get our hands on – the tagged corpus used for the production of the Oxford suite of dictionaries. We could, in addition and when necessary, turn to other corpora, including the BAWE and the BNC. Our requirements for acceptable carrier sentences were similar to those of Smith et al (2010), but were considerably more stringent.

To cut quite a long story short, we learnt fairly quickly that we simply couldn’t automate the generation of carrier sentences with sufficient consistency or reliability. As with some of the other examples discussed in this post, we were able to use the technology to help the writers in their work. We also learnt (rather belatedly, it has to be admitted) that we were trying to find technological solutions to problems that we hadn’t adequately analysed at the start. We hadn’t, for example, given sufficient thought to learner differences, especially the role of L1 (and other languages) in learning English. We hadn’t thought enough about the ‘messiness’ of either language or language learning. It’s possible, given enough resources, that we could have found ways of improving the algorithms, of leveraging other tools, or of deploying additional databases (especially learner corpora) in our quest for a personalised vocabulary learning system. But, in the end, it became clear to me that we were only nibbling at the problem of vocabulary learning. Deliberate learning of vocabulary may be an important part of acquiring a language, but it remains only a relatively small part. Technology may be able to help us in a variety of ways (and much more so in testing than learning), but the dreams of the data scientists (who wrote much of the research cited here) are likely to be short-lived. Experienced writers and editors of learning materials will be needed for the foreseeable future. And truly personalized vocabulary learning, fully supported by technology, will not be happening any time soon.



Fenogenova, A. & Kuzmenko, E. 2016. Automatic Generation of Lexical Exercises Available online at

Iwata, T., Goto, T., Kojiri, T., Watanabe, T. & T. Yamada. 2011. ‘Automatic Generation of English Cloze Questions Based on Machine Learning’. NTT Technical Review Vol. 9 No. 10 Oct. 2011

Kilgarriff, A. et al. 2008. ‘GDEX: Automatically Finding Good Dictionary Examples in a Corpus.’ In E. Bernal and J. DeCesaris (eds.), Proceedings of the XIII EURALEX International Congress: Barcelona, 15-19 July 2008. Barcelona: l’Institut Universitari de Lingüística Aplicada (IULA) dela Universitat Pompeu Fabra, 425–432.

Knoop, S. & Wilske, S. 2013. ‘WordGap – Automatic generation of gap-filling vocabulary exercises for mobile learning’. Proceedings of the second workshop on NLP for computer-assisted language learning at NODALIDA 2013. NEALT Proceedings Series 17 / Linköping Electronic Conference Proceedings 86: 39–47. Available online at

Kumar, G., Banchs, R.E. & D’Haro, L.F. 2015. ‘RevUP: Automatic Gap-Fill Question Generation from Educational Texts’. Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications, 2015, pp. 154–161, Denver, Colorado, June 4, Association for Computational Linguistics

Smith, S., Avinesh, P.V.S. & Kilgariff, A. 2010. ‘Gap-fill tests for Language Learners: Corpus-Driven Item Generation’. Proceedings of ICON-2010: 8th International Conference on Natural Language Processing, Macmillan Publishers, India. Available online at

Susanti, Y., Iida, R. & Tokunaga, T. 2015. ‘Automatic Generation of English Vocabulary Tests’. Proceedings of 7th International Conference on Computer Supported Education. Available online

Susanti, Y., Tokunaga, T., Nishikawa, H. & H. Obari 2017. ‘Evaluation of automatically generated English vocabulary questions’ Research and Practice in Technology Enhanced Learning 12 / 11