The 1st Workshop on Automatic Simultaneous Translation

Challenges, Recent Advances, and Future Directions

Workshop at ACL 2020, Seattle, July 9 or 10, 2020
Contact: autosimtrans.workshop@gmail.com or twitter.com/autosimtrans

Overview

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), is becoming a cutting-edge research field.

As an emerging and interdisciplinary field, simultaneous translation faces many great challenges, and is considered one of the holy grails of AI. As an evidence of the growing importance of simultaneous translation within NLP, one of us (Liang) gave an invited talk at ACL 2018 on the recent advances in this field. This 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:

  • The architecture of simultaneous translation: 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;
  • Machine aided simultaneous translation (MAST): improve the efficiency and quality of human interpreters;

Meanwhile, the workshop will also explore challenges for developing practical simultaneous translation systems and will provide opportunity for participants show their products.

We introduce two submission tracks in this workshop: a shared task track for simultaneous translation quality and latency competition; and a research track for related research paper submissions (see more details below).

Shared Task

We plan to organize a simultaneous translation shared task on Chinese-English and English-Spanish. We will provide open dataset and evaluation environment. Participants are asked to submit their system in docker and system description.

This year, we have released Baidu Speech Translation Corpus (BSTC) for open research, which covers speeches in a wide range of domains, including IT, economy, culture, biology, arts, etc. We also held an SiMT evaluation campaign collaborated with China Conference on Machine Translation (CCMT). The evaluation campaign has attracted 14 participants. We will enlarge the corpus and extend the language pairs for the workshop shared task. The shared task is hope to attract more than 10 participants.

For more information, please see the Shared Task page.

Research Track

For more information, please see Call for Papers.

Invited Keynote Speakers (confirmed)

We have two sets of keynote speakers: 4 from simultaneous translation, and 2 from human interpretation research. We hope this workshop will greatly increase the communication and crossfertilization between the two fields. All these speakers are confirmed.

Simultaneous Translation Speakers
  • Jordan Boyd-Graber, Associate Professor, University of Maryland, USA
  • Colin Cherry, Research Scientist in Google Translate, Google Inc., Montreal, Canada
  • Qun Liu,Chief Scientist of Speech and Language Computing,Huawei Noah’s Ark Lab,China
  • Hua Wu, Chief Scientist of NLP, Baidu Inc., China
Human Interpretation Speakers:
  • Kay-Fan Cheung, The Hong Kong Polytechnic University, and Member of the International Association of Conference Interpreters (AIIC), China
  • Barry Slaughter Olsen, the Middlebury Institute of International Studies and Conference Interpreter, and Member of the International Association of Conference Interpreters (AIIC), USA

Awards

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

Financial Assistance

We can offer partial financial aid to student authors who demonstrate significant financial need. Instructions on how to apply for financial assistance will be provided after paper acceptance decisions have been finalized.

Organizing Committee

  • Hua Wu, Baidu Inc., China, E-mail: wu_hua@baidu.com
  • Colin Cherry, Google, Canada, E-mail: colincherry@google.com
  • Liang Huang, Oregon State University and Baidu Research, USA, E-mail: lianghuang@baidu.com
  • Zhongjun He, Baidu Inc., China, E-mail: hezhongjun@baidu.com
  • Mark Liberman, Univ. of Pennsylvania, USA, E-mail: myl@ling.upenn.edu
  • James Cross, Facebook, USA, E-mail: jcross@fb.com
  • Yang Liu, Tsinghua University, China, E-mail: liuyang2011@tsinghua.edu.cn

Program Committee

Please see Invitation to Sponsor AutoSimTrans for sponsorship details.