论视觉基础PCFG的可迁移性
On the Transferability of Visually Grounded PCFGs
AI总结：
本研究评估视觉基础PCFG的跨域可迁移性，通过扩展VC-PCFG并在零样本迁移设置下实验，发现视觉基础的好处仅在相似域间有效，词汇重叠是影响可迁移性的关键因素。
摘要：
近年来，视觉基础语法归纳引起了极大的研究兴趣。尽管已为该任务开发了多种模型并展现出令人印象深刻的性能，但它们尚未在与训练域不同的文本域上进行评估，因此尚不清楚视觉基础带来的改进是否具有可迁移性。本研究旨在填补这一空白并评估可迁移性的程度。我们首先扩展了VC-PCFG（Visually-grounded Compound PCFG的简称），使其能够跨文本域迁移。我们考虑一种零样本迁移学习设置，即模型在源域上训练并直接应用于目标域，无需任何进一步训练。实验结果表明：使用视觉基础带来的好处可以迁移到与训练域相似的文本域中，但无法迁移到相距较远的域中。此外，我们进行了数据和结果分析；我们发现源域和目标域之间的词汇重叠是VC-PCFG可迁移性最重要的因素。
英文摘要：
There has been a significant surge of interest in visually grounded grammar induction in recent times. While a variety of models have been developed for the task and have demonstrated impressive performance, they have not been evaluated on text domains that are different from the training domain, so it is unclear if the improvements brought by visual groundings are transferable. Our study aims to fill this gap and assess the degree of transferability. We start by extending VC-PCFG (short for Visually-grounded Compound PCFG~\citep{zhao-titov-2020-visually}) in such a way that it can transfer across text domains. We consider a zero-shot transfer learning setting where a model is trained on the source domain and is directly applied to target domains, without any further training. Our experimental results suggest that: the benefits from using visual groundings transfer to text in a domain similar to the training domain but fail to transfer to remote domains. Further, we conduct data and result analysis; we find that the lexicon overlap between the source domain and the target domain is the most important factor in the transferability of VC-PCFG.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
