Generating example contexts to help children learn word meaning

Abstract

This article addresses the problem of generating good example contexts to help children learn vocabulary. We describe VEGEMATIC, a system that constructs such contexts by concatenating overlapping five-grams from Google's N-gram corpus. We propose and operationalize a set of constraints to identify good contexts. VEGEMATIC uses these constraints to filter, cluster, score, and select example contexts. An evaluation experiment compared the resulting contexts against human-authored example contexts (e.g., from children's dictionaries and children's stories). Based on rating by an expert blind to source, their average quality was comparable to story sentences, though not as good as dictionary examples. A second experiment measured the percentage of generated contexts rated by lay judges as acceptable, and how long it took to rate them. They accepted only 28% of the examples, but averaged only 27 seconds to find the first acceptable example for each target word. This result suggests that hand-vetting VEGEMATIC's output may supply example contexts faster than creating them manually. † This work, performed while the first author was a Master's student in the Language

The impact of internal-generated contextual clues on EFL vocabulary learning: insights from EEG

“…For the external-provided contextual clue (condition a), example sentences for all words were sourced from online dictionaries (e.g., Youdao, Oxford, and Collins) by three English major postgraduates independently. These dictionary-derived example sentences were considered of high quality and suitable for facilitating vocabulary comprehension (Friedman, 2009;Liu and Mostow, 2013). Two English professors further reviewed and revised these sentences to ensure their appropriateness.…”

“…Existing research suggests two ways of accessing contextual clues for semantic processing in vocabulary learning. First, related contexts can be provided by learning materials, such as example sentences accompanied by unknown words (Liu and Mostow, 2013). Example sentences with translations in the learners' native language act as valuable scaffolding, especially for EFL learners with lower language proficiency (Jimenez and Kanoh, 2012;Pauwels, 2012).…”

A vocabulary acquisition framework using audio books

“…( 1) indicates sum of paths, and it transforms to the Viterbi algorithm if the summation is replaced with a max operation, as shown in Eq. (2).…”

“…Intentional learning is often encountered when a child or an adult is learning a second language. Earlier techniques for intentional learning include -1) flash cards promoting intentional memorization, 2) use of pictures and the associated description such as Rosetta Stone (http://www.rosettastone.com), 3) retrieval of appropriate reading material from the Internet [1] and 4) generation of a pseudo-sentence/phrase for practice [2]. Techniques for incidental acquisition include -1) speech enabled card games [3] and 2) task based vocabulary learning [4].…”

Procedural content generation for VR educational applications: The investigation of AI-based approaches for improving learning experience

“…To overcome this issue, the integration of Machine Learning (ML) and Reinforcement Learning (RL) algorithms into their Procedural Content Generation (PCG) methods for automatically generating new content that is tailored to educational applications has been studied. In the textual educational content area, previous research has explored the use of ML algorithms for generating educational content such as vocabulary contexts and quiz questions [12][13][14], as well as using crowdsourced rating method to identify nutritious content [15]. These studies demonstrate the potential of ML algorithms to automate the generation of nutritious educational content, which can be time-consuming and challenging for humans to undertake.…”