# A Comparative Study of Word Embeddings for Reading Comprehension

arXiv: https://arxiv.org/abs/1703.00993 · HTML: https://mlsanity.com/paper/1703.00993/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2017.

## Built on by (most cited first, 4 of 4)

- [Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing](https://mlsanity.com/paper/2103.01009/) (2021)
- [Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units](https://mlsanity.com/paper/2106.04935/) (2021)
- [A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches](https://mlsanity.com/paper/2303.07196/) (2023)
- [Deep Neural Networks for Visual Reasoning](https://mlsanity.com/paper/2209.11990/) (2022)

## Abstract (arXiv)

The focus of past machine learning research for Reading Comprehension tasks has been primarily on the design of novel deep learning architectures. Here we show that seemingly minor choices made on (1) the use of pre-trained word embeddings, and (2) the representation of out-of-vocabulary tokens at test time, can turn out to have a larger impact than architectural choices on the final performance. We systematically explore several options for these choices, and provide recommendations to researchers working in this area.