United States

Pre-trained contextual vision-and-language (V&amp;L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to collect and require cumbersome curation. Inspired by unsupervised machine translation, we investigate if a strong V&amp;L representation model can be learned through unsupervised pre-training without image-caption corpora. In particular, we propose to conduct &quot;mask-and-predict&quot; pre-training on text-only and image-only corpora and introduce the object tags detected by an object recognition model as anchor points to bridge two modalities. We find that such a simple approach achieves performance close to a model pre-trained with aligned data, on four English V&amp;L benchmarks. Our work challenges the widely held notion that aligned data is necessary for V&amp;L pre-training, while significantly reducing the amount of supervision needed for V&amp;L models.

NAACL 2021

Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to collect and require cumbersome curation. Inspired by unsupervised machine translation, we investigate if a strong V&L representation model can be learned through unsupervised pre-training without image-caption corpora. In particular, we propose to conduct "mask-and-predict" pre-training on text-only and image-only corpora and introduce the object tags detected by an object recognition model as anchor points to bridge two modalities. We find that such a simple approach achieves performance close to a model pre-trained with aligned data, on four English V&L benchmarks. Our work challenges the widely held notion that aligned data is necessary for V&L pre-training, while significantly reducing the amount of supervision needed for V&L models.

technical paper

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies

Nutribullets Hybrid: Multi-document Health Summarization

AVA: an Automatic eValuation Approach for Question Answering Systems

SpanPredict: Extraction of Predictive Document Spans with Neural Attention

Text Editing by Command

A Deep Metric Learning Approach to Account Linking

Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation

MIMOQA: Multimodal Input Multimodal Output Question Answering

Multimodal End-to-End Sparse Model for Emotion Recognition

OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding

https://d3smihljt9218e.cloudfront.net/transcript/13403/subtitle/924191efcb14e0a8c17965fdba585760.vtt

English (automatic)

Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions

Downloads

Next from NAACL 2021

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies

Similar lecture

Sampling and Filtering of Neural Machine Translation Distillation Data