Solving ESL Sentence Completion Questions via Pre-trained Neural Language Models

TL;DR

This paper introduces a neural approach using pre-trained language models to automatically solve ESL sentence completion questions, demonstrating high accuracy on real-world K-12 datasets and discussing deployment considerations.

Contribution

It presents a novel neural framework leveraging pre-trained models specifically for ESL sentence completion tasks, with extensive experiments validating its effectiveness.

Findings

Model outperforms baselines in accuracy

Effective in real-world K-12 datasets

Analyzes practical deployment trade-offs

Abstract

Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options. SC questions are widely used for students learning English as a Second Language (ESL) and building computational approaches to automatically solve such questions is beneficial to language learners. In this work, we propose a neural framework to solve SC questions in English examinations by utilizing pre-trained language models. We conduct extensive experiments on a real-world K-12 ESL SC question dataset and the results demonstrate the superiority of our model in terms of prediction accuracy. Furthermore, we run precision-recall trade-off analysis to discuss the practical issues when deploying it in real-life scenarios. To encourage reproducible results, we make our code publicly available at \url{https://github.com/AIED2021/ESL-SentenceCompletion}.