Call For Papers

It’s our pleasure to hold the first workshop on Document Images and Language (DIL). Multi-modality in artificial intelligence has become a promising trend nowadays and NLP technology has gained a rapid development in recent years. In order to accelerate the utilization of text modality in document image understanding, we provide this platform for the frontier works on the combination of these two areas. The workshop aims to link the researchers from both document image understanding and NLP communities to bring more inspiration. We encourage the authors to submit papers on the topics below.

Topics:

Submission:

The first DIL is calling for original and unpublished papers on topics of interest as above. Papers have to be submitted via the workshop's Easychair submission page. We will follow a single blind review process and each paper will be reviewed by at least two reviewers. Since this year, the ICDAR main conference planned to publish the proceedings with Springer LNCS, papers should be formatted according to LNCS instructions for authors.

We welcome the following types of contributions:

  • Full research papers (12-15 pages): finished or consolidated R&D works, to be included in one of the Workshop topics
  • Short papers (6-8 pages): ongoing works with relevant preliminary results, opened to discussion.
  • Contact:

    ocr-nlp.workshop@baidu.com