# InDEX: Indonesian Idiom and Expression Dataset for Cloze Test

arXiv: https://arxiv.org/abs/2211.13376 · HTML: https://mlsanity.com/paper/2211.13376/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 24 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations](https://mlsanity.com/paper/1511.02301/) (2015)
- [ChID: A Large-scale Chinese IDiom Dataset for Cloze Test](https://mlsanity.com/paper/1906.01265/) (2019)
- [CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension](https://mlsanity.com/paper/1803.09720/) (2018)
- [Large-scale Cloze Test Dataset Created by Teachers](https://mlsanity.com/paper/1711.03225/) (2017)
- [Who did What: A Large-Scale Person-Centered Cloze Dataset](https://mlsanity.com/paper/1608.05457/) (2016)
- [A BERT-based Dual Embedding Model for Chinese Idiom Prediction](https://mlsanity.com/paper/2011.02378/) (2020)
- [Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension](https://mlsanity.com/paper/2011.04499/) (2020)

## Abstract (arXiv)

We propose InDEX, an Indonesian Idiom and Expression dataset for cloze test. The dataset contains 10438 unique sentences for 289 idioms and expressions for which we generate 15 different types of distractors, resulting in a large cloze-style corpus. Many baseline models of cloze test reading comprehension apply BERT with random initialization to learn embedding representation. But idioms and fixed expressions are different such that the literal meaning of the phrases may or may not be consistent with their contextual meaning. Therefore, we explore different ways to combine static and contextual representations for a stronger baseline model. Experimentations show that combining definition and random initialization will better support cloze test model performance for idioms whether independently or mixed with fixed expressions. While for fixed expressions with no special meaning, static embedding with random initialization is sufficient for cloze test model.