arXiv:2010.06775cs.CL
Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore the idea of a visually-supervised language model in this paper. We find that the main reason hindering this exploration is the large divergence in magnitude and distributions between the visually-grounded language datasets and pure-language corpora. Therefore, we develop a technique named "vokenization" that extrapolates multimodal alignments to language-only data by contextually mapping language tokens to their related images (which we call "vokens"). The "vokenizer" is trained on relatively small image captioning datasets and we then apply it to generate vokens for large language corpora. Trained with these contextually generated vokens, our visually-supervised language models show consistent improvements over self-supervised alternatives on multiple pure-language tasks such as GLUE, SQuAD, and SWAG. Code and pre-trained models publicly available at https://github.com/airsplay/vokenization
It's a super cool paper that invents "vokenization" to generate a large amount of visually-grounded language datasets and trains visually-grounded models on those. Most language models are trained on pure text data. Although it achieves significant success in recent years, this…
deeplstmView on HNParent context