王 瑞 (Wang, Rui)
Tenure-track Researcher
Advanced Translation Technology Laboratory, NICT, Kyoto, Japan
Dr. Rui Wang is a computational linguist working as a tenure-track researcher in NICT. His research focuses on machine translation (MT), a classic task in NLP (or even in AI). His recent interests are traditional linguistic based and cutting-edge machine learning based approaches for MT. He (as the first or the corresponding authors) has published more than 30 MT papers in top-tier NLP/ML/AI conferences and journals, such as ACL, EMNLP, ICLR, AAAI, IJCAI, IEEE/ACM transactions, etc. He has also won several first places in top-tier MT/NLP shared tasks, such as WMT-2018, WMT-2019, CoNLL-2019 etc. He served as the area co-chairs of CCL-2018/2019 and the organization co-chairs of PACLIC-29 and YCCL-2012.
In 2020/04, three linguistic motivated NMT papers were accpeted by ACL-2020, including [Multi-lingual Unsupervised NMT], [Context Gates], and [Content Word (to appear)]
In 2019/12, two machine leanring motivated NMT papers [Data-dependent Objective] (with the full review score) and [Universal Visual NMT] were accepted (both oral) by ICLR-2020.
In 2019/05, four linguistic motivated NMT papers were accepted by ACL-2019, including [Unsupervised NMT], [Reordering], [Sentence-Level Agreement], and [Lattice Encoder].
In 2019/04, we (with Haipeng, Benjamin, and Kehai) won the first place in WMT-2019 unsupervised MT task (German-Czech) by BLEU [Result] and human evaluation [Paper].
In 2018/05, Benjamin and I won the first places of four tasks (English<->Estonian and English<->Finnish) in WMT-2018 [Results by BLEU] [Results by Human][Our Paper].
In 2017 and 2018, I focused on domain adaptation papers for NMT, including [Revisiting SMT] (COLING-2016), [Data Selection] (ACL-2017), [Instance Weighting] (EMNLP-2017), [Curriculum Learning] (ACL-2018), [Survey] (COLING-2018), and [Summary Journal] (TASLP-2018).
From 2013 to 2016, I focused on continuous-space representations for SMT, inlcuding [Monolingual NNLM] (EMNLP-2013), [Bilingual NNLM] (EMNLP-2014), [Summary Journal] (TASLP-2015), [Graph-based Word Embedding] (IJCAI-2016), and [Summary Journal] (TALLIP-2018).
News
From 2020, I will serve in the standing reviewer teams of the TACL and CL journal.
A good research paper (similar to figure skating) = a high technical merit + a brilliant presentation. [6.0 system (reality)] [ISU Judging System (ideal)]