Jack Merullo

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

2022 · arXiv (Cornell University)

Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode compositional representations of the concepts over which they …

ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution

2022 · arXiv (Cornell University)

Large-scale, high-quality corpora are critical for advancing research in coreference resolution. However, existing datasets vary in their definition of coreferences and have been collected via complex and lengthy guidelines that are curated for linguistic experts. …