A Comparative Study of Word Embeddings for Reading Comprehension
Not on the map. Why?
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.
Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). First posted on arXiv 2 Mar 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 1; 2023: 1.
4 papers.
- 2021Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezingcited by 7
- 2021Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Unitscited by 2
- 2023A Comprehensive Empirical Evaluation of Existing Word Embedding Approachescited by 1
- 2022Deep Neural Networks for Visual Reasoningcited by 0
- 2023A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches13 Mar 2023
- 2022Deep Neural Networks for Visual Reasoning24 Sep 2022
- 2021Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units9 Jun 2021
- 2021Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing1 Mar 2021