Dear all EAMT members, I'm Toshiaki Nakazawa from The University of Tokyo, Japan. This is the 2nd call for participation for the MT shared tasks and research papers to the 7th Workshop on Asian Translation (WAT2020), workshop of AACL-IJCNLP 2020. Those who are working on machine translation, please join us.
UPDATES -------------- - details of Japanese <--> English multimodal task is out https://nlab-mpg.github.io/wat2020-mmt-jp/ - newly added 2 document-level translation tasks ParaNatCom: English --> Japanese Scientific Paper http://lotus.kuee.kyoto-u.ac.jp/WAT/WAT2020/aspec_doc.html BSD Corpus: English <--> Japanese Business Scene Dialogue http://lotus.kuee.kyoto-u.ac.jp/WAT/WAT2020/bsd.html IMPORTANT DATES --------------- August 28, 2020 Translation Task Submission Deadline September 18, 2020 – Research Paper Submission Deadline October 23, 2020 – Notification of Acceptance for Research Papers October 23, 2020 System Description Paper Submission Deadline October 30, 2020 Review Feedback of System Description Papers November 6, 2020 - Camera-ready Deadline December 4-7, 2020 Workshop Dates (one of these days) * All deadlines are calculated at 11:59PM UTC-12 Best regards, --------------------------------------------------------------------------- WAT2020 (The 7th Workshop on Asian Translation) in conjunction with AACL-IJCNLP2020 http://lotus.kuee.kyoto-u.ac.jp/WAT/ December 4-7, 2020, Suzhou, China (ONLINE) Following the success of the previous WAT workshops (WAT2014 -- WAT2019), WAT2020 will bring together machine translation researchers and users to try, evaluate, share and discuss brand-new ideas about machine translation. For the 7th WAT, we will include the following new translation tasks: * Document-level translation tasks - English --> Japanese scientific paper abstract task - English <--> Japanese business scene dialogue task * Japanese <--> English multimodal task * Document-level test set for Japanese <--> English newswire task * Hindi/Thai/Malay/Indonesian <--> English IT-domain and Wikinews task * Odia <--> English mixed-domain task together with the following continuing tasks: * English/Chinese <--> Japanese scientific paper task * English/Chinese/Korean <--> Japanese patent task * English <--> Japanese newswire task * Russian <--> Japanese news commentary task * Myanmar <--> English mixed-domain task * Khmer <--> English mixed-domain task * Indian language <--> English mixed-domain multilingual translation task * English --> Hindi multimodal task In addition to the shared tasks, the workshop will also feature scientific papers on topics related to the machine translation, especially for Asian languages. Topics of interest include, but are not limited to: - analysis of the automatic/human evaluation results in the past WAT workshops - word-/phrase-/syntax-/semantics-/rule-based, neural and hybrid machine translation - Asian language processing - incorporating linguistic information into machine translation - decoding algorithms - system combination - error analysis - manual and automatic machine translation evaluation - machine translation applications - quality estimation - domain adaptation - machine translation for low resource languages - language resources ************************* IMPORTANT NOTICE ************************* Participants of the previous workshop are also required to sign up to WAT2020 ******************************************************************** TRANSLATION TASKS ----------------- The task is to improve the text translation quality for scientific papers and patent documents. Participants choose any of the subtasks in which they would like to participate and translate the test data using their machine translation systems. The WAT organizers will evaluate the results submitted using automatic evaluation and human evaluation. We will also provide a baseline machine translation. Tasks: Document-level Translation tasks: (NEW!) ParaNatCom: English --> Japanese Scientific Paper BSD Corpus: English <--> Japanese Business Scene Dialogue Scientific Paper: [Asian Scientific Paper Excerpt Corpus (ASPEC)] English/Chinese <--> Japanese Patent: [Japan Patent Office Patent Corpus 2.0 (JPC2)] English/Chinese/Korean <--> Japanese Newswire: [JIJI Corpus] (document-level testset is newly added) Japanese <--> English News Commentary: Japanese <--> Russian (Japanese <--> English and English <--> Russian included) IT Documentation and Wikinews: [SAP-NICT Corpus] Hindi/Thai/Malay/Indonesian <--> English [ALT and other mixed corpora] NEW!! Mixed domain: Myanmar <--> English [UCSY and ALT corpora] Khmer <--> English [ECCC and ALT corpora] Indic: Indian Language <--> English multilingual [Assorted Corpus from various sources] Odia <--> English [UFAL (EnOdia) corpus] NEW!! Multimodal: Hindi --> English Multimodal [Hindi Visual Genome corpus] Japanese <--> English Multimodal [Flickr30kEnt-JP corpus] NEW!! Dataset: * Scientific paper WAT uses ASPEC for the dataset including training, development, development test and test data. Participants of the scientific papers subtask must get a copy of ASPEC by themselves. ASPEC consists of approximately 3 million Japanese-English parallel sentences from paper abstracts (ASPEC-JE) and approximately 0.7 million Japanese-Chinese paper excerpts (ASPEC-JC) * Patent WAT uses JPO Patent Corpus, which is constructed by Japan Patent Office (JPO). This corpus consists of 1 million English-Japanese parallel sentences, 1 million Chinese-Japanese parallel sentences, and 1 million Korean-Japanese parallel sentences from patent description with four categories. Participants of patent tasks are required to get it on WAT2019 site of JPO Patent Corpus. - English/Chinese/Korean <--> Japanese: These tasks evaluate performance of a translation model similarly as the other translation tasks. Differing from the previous tasks at WAT2015, WAT2016 and WAT2017, new test sets of these tasks consists of (a) patent documents published between 2011 and 2013, which were used in the past years' WAT, and (b) ones published between 2016 and 2017 for each language pair. We will also evaluate performance of the section (a) so as to compare systems submitted in the past years' WAT. - Chinese -> Japanese expression pattern task: This task evaluates performance of a translation model for each predifined category of expression patterns, which corresponds to title of invention (TIT), abstract (ABS), scope of claim (CLM) or description (DES). Test set of this task consists of sentences each of which is annotated with a corresponding category of expression patterns. * Newswire WAT uses JIJI Corpus, which is constructed by Jiji Press Ltd. in collaboration with the National Institute of Information and Communications Technology (NICT). This corpus consists of a Japanese-English news corpus of 200K parallel sentences, from Jiji Press news with various categories. At WAT2020, the organizers newly added a new document-level translation testset, which consists of manually filtered test and reference sentences and document-level context of the test sentences. Participants of the newswire subtask are required to get it on WAT2020 site of JIJI Corpus. * News Commentary WAT uses a manually aligned and cleaned Japanese <--> Russian corpus from the News Commentary domain to study extremely low resource situations for distant language pairs. The parallel corpus contains around 12,000 lines. This year, we invite participants to utilize any existing monolingual or parallel corpora from WMT 2020 in addition to those listed on the WAT website. In particular, solutions focusing on monolingual pretraining and multilingualism are encouraged. * IT and Wikinews - Hindi/Thai/Malay/Indonesian <--> English In collaboration with SAP and NICT, WAT is organising a pilot translation task to/from English to/from Hindi, Thai, Malay and Indonesian. The evaluation data belongs to the IT domain (Software Documentation) and Wikinews domain (Asian Language Treebank). Participants will be expected to train systems and submit translations for all language pairs (to and from English) and both domains using any existing monolingual or parallel data. Given the growing focus on a universal translation model for multiple languages and domains, WAT encourages a single multilingual and multi-domain model for all language pairs and both domains (IT as well as Wikinews). Additional details will be given on the WAT 2020 website. * Mixed domain - Myanmar (Burmese) <--> English WAT uses UCSY Corpus and ALT Corpus. The UCSY corpus and a portion of the ALT corpus are use as training data, which are around 220,000 lines of sentences and phrases. The development and test data are from the ALT corpus. - Khmer <--> English WAT uses ECCC Corpus and ALT Corpus. The ECCC corpus and a portion of the ALT corpus are use as training data, which are around 120,000 lines of sentences and phrases. The development and test data are from the ALT corpus. * Indic - Odia <--> English For the first time, WAT organizing a translation task for the low resource language Odia. WAT will use the OdiEnCorp2.0 corpus collected by researchers at Idiap Research Institute and UFAL. The training data contains around 98K parallel sentences covering different domains. - Indian language <--> English multilingual translation task. This task is being revived after 2018 with major revisions. There has been an increase in the available datasets for Indian languages in the last couple of years along with major advances in multilingual learning. The task will involve training a single model for multiple Indian languages to English (and vice-versa) translation. The goal is to encourage exploration of methods which utilize language relatedness to improve translation quality for low-resource languages while having a single, compact translation model. The training set would be compiled from many publicly available datasets spanning 7-8 Indian languages. * Multimodal - Hindi --> English Multimodal (Visual Genome) After a warm response from the participants for the “WAT 2019 Multimodal Translation Task”, WAT will continue organizing a multimodal English --> Hindi translation task where the input will be text and an Image and the output will be a caption (text). The training set contains around 30,000 segments. Additional details will be given on the task website. - Japanese <--> English Multimodal (Flickr30kEnt-JP) Details of this task will be announced later. We will use the Flickr30kEnt-JP corpus for this task. https://github.com/nlab-mpg/Flickr30kEnt-JP EVALUATION ---------- Automatic evaluation: We are providing an automatic evaluation server. It is free for everyone, but you need to create an account for evaluation. Just showing the list of evaluation results does not require an account. Sign-up: http://lotus.kuee.kyoto-u.ac.jp/WAT/WAT2020/ Eval. result: http://lotus.kuee.kyoto-u.ac.jp/WAT/evaluation/ Human evaluation: Both crowdsourcing evaluation and JPO adequacy evaluation will be carried out for selected subtasks and selected submitted systems (the details will be announced later). INVITED TALK ------------ TBA ORGANIZERS ---------- Toshiaki Nakazawa, The University of Tokyo, Japan Hideki Nakayama, The University of Tokyo, Japan Chenchen Ding, National Institute of Information and Communications Technology (NICT), Japan Raj Dabre, National Institute of Information and Communications Technology (NICT), Japan Hiroshi Manabe, National Institute of Information and Communications Technology (NICT), Japan Anoop Kunchukuttan, Microsoft, India Win Pa Pa, University of Computer Studies, Yangon (UCSY), Myanmar Ondřej Bojar, Charles University, Prague, Czech Republic Shantipriya Parida, Idiap Research Institute, Martigny, Switzerland Isao Goto, Japan Broadcasting Corporation (NHK), Japan Hidaya Mino, Japan Broadcasting Corporation (NHK), Japan Katsuhito Sudoh, Nara Institute of Science and Technology (NAIST), Japan Sadao Kurohashi, Kyoto University, Japan Pushpak Bhattacharyya, Indian Institute of Technology Bombay (IITB), India CONTACT ------- [email protected] _______________________________________________ Mt-list site list [email protected] http://lists.eamt.org/mailman/listinfo/mt-list
