Dirk Groeneveld

Did you mean to say "two or more"?

RoBERTa on SuperGLUE's 'Multi-Sentence Reading Comprehension' task

1

MultiRC is one of the tasks of the [SuperGLUE](https://super.gluebenchmark.com) benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and build an AllenNLP config that reads the...

Adds two Tango steps that keep only the strings from a dataset

Train T5 on MATH

2

We should try to train T5 on the MATH dataset (https://arxiv.org/abs/2103.03874). Performance is expected to be poor: GPT2 gets under 7%. This dataset was specifically constructed to thwart transformer models,...

RoBERTa on SuperGLUE's 'Reading Comprehension with Commonsense Reasoning' task

9

ReCoRD is one of the tasks of the [SuperGLUE](https://super.gluebenchmark.com) benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and build an AllenNLP config that reads the...

We want to implement the Caption-Based Image Retrieval task from https://api.semanticscholar.org/CorpusID:199453025. The [COCO](https://cocodataset.org/) and [Flickr30k](https://www.kaggle.com/hsankesara/flickr-image-dataset) datasets contain a large number of images with image captions. The task here is to...

Visual Genome has a set of questions for every image, 1.7M in total. This task is about `Step` that produces a `DatasetDict` for this task, and then some more steps...

RoBERTa on SuperGLUE's Broadcoverage Diagnostics task

4

Broadcoverage Diagnostics is one of the tasks of the [SuperGLUE](https://super.gluebenchmark.com) benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and build an AllenNLP config that reads...

Winogender Schema Diagnostics (AX-g) is one of the tasks of the [SuperGLUE](https://super.gluebenchmark.com) benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and build an AllenNLP config...

WSC is one of the tasks of the [SuperGLUE](https://super.gluebenchmark.com) benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and build an AllenNLP config that reads the...