On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “SQuAD2.0”

Gestalt: a Stacking Ensemble for SQuAD2.0cs.CL

Gestalt combines two models to improve SQuAD2.0 performance.

problem Improving the accuracy of answering questions in context paragraphs.

method A stacking ensemble of ALBERT and RoBERTa models, combined with a CNN-based meta-model.

result Best ensemble achieved 87.117 EM and 90.306 F1 scores, improving baseline by 0.55% and 0.61% respectively.

SQuAD2.0 deep learning ensemble learning meta-model context paragraph

2020-04-02abs ↗pdf ↗

Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0cs.CL

Paper explores BERT's efficiency on SQuAD2.0, freezing layers and using adapters.

problem Improving BERT's efficiency for SQuAD2.0 while maintaining performance.

method Freezing transformer layers, using adapters, and context-aware convolutional filters.

result Context-aware convolutional filters do not improve practical efficiency.

BERT Stanford Question Answering SQuAD2.0 Parameter Efficiency Adapters

2020-02-25abs ↗pdf ↗

EQuANt (Enhanced Question Answer Network)cs.CL

Machine Reading Comprehension (MRC) is an important topic in the domain of automated question answering and in natural language processing more generally. Since the release of the SQuAD 1.1 and SQuAD 2 datasets, progress in the field has been particularly significant, with current state-of-the-art models now exhibiting…

2019-06-24abs ↗pdf ↗

Undersensitivity in Neural Reading Comprehensioncs.CL

Neural models often incorrectly predict the same answer to subtly changed questions, even when they should not.

problem Neural models' oversensitivity to adversarial question changes.

method Formulated a noisy adversarial attack to identify and exploit undersensitivity, tested with data augmentation and adversarial training.

result Undersensitivity can be exploited to mislead models, and addressing it improves model performance and robustness.

Neural Reading Comprehension Adversarial Attacks Model Vulnerability Data Augmentation Adversarial Training

2020-02-15abs ↗pdf ↗