SQuAD-SRC: A Dataset for Multi-Accent Spoken Reading Comprehension

Authors: Yixuan Tang, Anthony K.H: Tung

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present a statistical analysis of our SQu AD-SRC dataset and conduct extensive experiments on it by comparing cascaded SRC approaches and the enhanced endto-end ones.
Researcher Affiliation Academia Yixuan Tang , Anthony K.H. Tung Department of Computer Science, National University of Singapore
Pseudocode No The paper describes methods using text and diagrams, but does not contain structured pseudocode or algorithm blocks.
Open Source Code No The SQu AD-SRC is available at https://github.com/tangyixuan/SQu AD-SRC. However, this link points to the dataset, not explicitly the source code for the methodology described in the paper.
Open Datasets Yes we introduce an open-source, large-scale, naturally recorded, multi-accent spoken reading comprehension (SRC) dataset named SQu AD-SRC.
Dataset Splits No We follow the same data partition of SQu AD and use the 87.6k examples from their entire training set for our training set, and 10.6k examples from their development set for our test set, since their test set is not made publicly available. The paper defines training and test sets but does not explicitly define a separate validation set for model tuning.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running experiments.
Software Dependencies No The paper mentions software models and frameworks used (e.g., wav2vec 2.0, BERT, Speech T5) but does not provide specific version numbers for these or other ancillary software components.
Experiment Setup No The paper describes model architectures and training approaches (e.g., fine-tuning) but does not provide specific experimental setup details such as hyperparameter values (learning rate, batch size, number of epochs) or optimizer settings.