First workshop on Transcript Understanding

17 October, 2022

Location: Gyeongju, Republic of Korea

Introduction

Thanks to the development of the Internet and video services such as YouTube, Facebook, and Twitch, people can easily share their own videos with people across continents on a daily basis. Along with books, these videos have become a new source of knowledge. However, the quality of information in some of these videos is sometimes questionable and may contain unintentional or intentional misinformation, and political bias.

Moreover, the COVID-19 pandemic has resulted in the widespread adoption of remote working, remote learning, and remote conferencing. These remote working environments demand many new applications for efficient video transcript understanding, such as meeting recording understanding, quality assurance in call centers, and automatic test scoring in educational testing. The recent advancements in methods and resources for speech recognition have also created more research opportunities around video transcript understanding.

Topics

The TU workshop holds a research track and a shared task track. The research track aims to explore recent advances and remaining challenges on video transcript understanding. As this topic is a multi-modal subject, researchers from artificial intelligence, computer vision, speech processing, natural language processing, data mining, statistics, and other fields are invited to submit papers on recent advances, resources, tools, challenges for video transcript understanding. To this end, the topics of the workshop include but are not limited to the following:

  • Fundamental processing for video transcript, such as punctuation restoration, chunking, parsing, and named entity recognition.
  • Subtitle segmentation
  • Text summarization and keyword extraction for transcripts
  • Event extraction, intent detection, and slot filling
  • Sentiment analysis for speech text processing
  • Noisy text processing
  • Fact-checking, evidence extraction
  • Question-Answering extraction from transcripts
  • Automatic Speech Recognition, and related system such as speaker identification and filler word detection
  • Multi-modal, multilingual video-speech-text processing
Important Dates
  • Papers Due: August 1, 2022 (Monday)
  • Papers Due: July 25, 2022 (Monday)
  • Notification of Acceptance: August 22, 2022 (Monday)
  • Camera-ready papers due: September 5, 2022 (Monday)
  • Workshop proceedings due: eptember 19, 2022 (Monday)
  • Workshop date: October 17, 2022

All deadlines are “anywhere on earth” (UTC-12)

Submission

Authors are invited to submit their unpublished work that represents novel research. The papers should be written in English using the *ACL style. Authors can also submit the supplementary materials, including technical appendices, source codes, datasets, and multimedia appendices. All submissions, including the main paper and its supplementary materials, should be fully anonymized. For more information on formatting and anonymity guidelines, please refer to COLING 2022 submission guidelines.

TU accepts both long papers (8 pages) and short papers (4 pages). The paper can include unlimited appendix and references. Upon the acceptance, the authors are provided with 1 more page to address the reviewer comments.

All papers will be double blind peer reviewed. Two reviewers with the same technical expertise will review each paper. Authors of the accepted papers will present their work in either the Oral or Poster session. All accepted papers will appear on the workshop proceedings that will be published on ACL Anthology.

Both research paper and shared task paper must be submitted using SoftConf at https://www.softconf.com/coling2022/TU/.

Contact us: vietl@uoregon.edu