The 3rd Workshop on Automatic Simultaneous Translation

Challenges, Recent Advances, and Future Directions

Workshop at NAACL 2022, Seattle, Friday July 15, 2022
Contact: autosimtrans.workshop@gmail.com or twitter.com/autosimtrans

Important Dates

  • 2022/03/07 00:00:00: Registration and release of data
  • 2022/04/30 23:59:59: End of registration
  • 2022/03/10 00:00:00: System submission begin
  • 2022/05/01 23:59:59: System submission close
  • 2022/05/14 00:00:00 Extended to 2022/05/17: System description due
  • 2022/06/01 00:00:00: Notification of acceptance
  • 2022/06/16 00:00:00: Camera-ready papers due

All submission deadlines are 11:59 PM GMT-12 (anywhere in the world) unless otherwise noted.

Description of the Workshop and Results from the First and the Second Workshop

(attached with ACL 2020 and NAACL 2021 respectively)

Simultaneous translation, which performs translation concurrently with the source speech, is widely useful in many scenarios such as international conferences, negotiations, press releases, legal proceedings, and medicine. It combines the AI technologies of machine translation (MT), automatic speech recognition (ASR), and text-to-speech synthesis (TTS) and is rapidly becoming a cutting-edge research field. As an emerging and interdisciplinary field, simultaneous translation faces many great challenges.

To promote the development in this field, we successfully held the first and the second workshop on simultaneous translation at ACL 2020 and NAACL 2021 respectively. We attracted 94 registered participants in 2020 and 96 registered participants in 2021. In the past two years, we invited 10 keynote speakers, 7 from simultaneous translation, and 3 from human interpretation research. We also held a shared task on Chinese-English simultaneous translation and released an open dataset Baidu Speech Translation Corpus (BSTC) for open research, which covers speeches in a wide range of domains, including IT, economy, culture, biology, arts, etc. The shared task attracted a total of 525 participants in the past two workshops (227 at ACL 2020 and 298 at NAACL 2021). The workshop also received 14 research paper submissions, with 11 accepted. The peak zoom attendance was 25 at ACL 2020 and 31 at NAACL 2021.

We have experiences of running a virtual workshop. All the talks and presentations are pre-recorded. We also run live Q\&As for each session to let all the speakers and attendees for further discussion.

Since simultaneous translation is an active and growing area in AI community, we propose to organize the third workshop in 2022. The workshop will bring together researchers and practitioners in machine translation, speech processing, and human interpretation, to discuss recent advances and open challenges of simultaneous translation, including:

  • Simultaneous translation paradigms: traditional pipeline (ASR-MT-TTS) or end-to-end (speech-speech);
  • Translation models: robust, high quality, and low latency;
  • Data resources: large and high-quality corpora for training simultaneous translation systems.
  • Evaluation methods: metrics to evaluate the translation quality and time latency;
  • Computer Aided Interpretation (CAI): improve the efficiency and quality of human interpreters;

Diversity

As in our first workshop, we have made efforts to promote diversity in our invited speakers, organizers, and PC. 1 out of 5 invited speakers are female, so are 2 out of 6 organizers, and 7 out of 20 PC members.

Virtual Conference

We are well prepared if our third workshop has to be a virtual conference just like our previous workshops at ACL 2020 and NAACL 2021. In fact, we think it would be easier for the invited speakers when no travel is needed. The only major challenge for running a virtual workshop is time zone coordination, as we have participants from Asia, Europe, and the Americas.

Sponsorships

  • Baidu
  • Huawei
  • Google

Awards

We will have a best paper award, a best presentation award, and a best poster award, sponsored by the above sponsors.