Overview of the 4th Workshop on Asian Translation

By Toshiaki Nakazawa, Shohei Higashiyama, Chenchen Ding, Hideya Mino, Isao Goto, Hideto Kazawa, Yusuke Oda, Graham Neubig, Sadao Kurohashi. 2017

47 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Graham Neubig
2. Marine Carpuat
3. Jiatao Gu
4. Taku Kudo
5. Chenhui Chu
6. Felix Stahlberg
7. Changhan Wang
8. Weijia Xu

In Evaluation & Benchmarks

1. Taku Kudo
2. Graham Neubig
3. Chenhui Chu
4. Rui Wang
5. Jiatao Gu
6. Sadao Kurohashi
7. Yusuke Oda
8. Hideto Kazawa

Citations in the corpus

• SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing (2018, background): “NMT has shown remarkable re-sults in several shared tasks (Denkowski and Neu-big, 2017; Nakazawa et al., 2017), and its effective approach has had a strong influence on other re-lated NLP tasks such as dialog generation (Vinyals and Le, 2015) and automatic summarization (Rush et al., 2015).”
• Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates (2018, methodology): “…1: Multiple subword sequences encoding the same sentence “Hello World” nrich et al., 2016) is a de facto standard sub-word segmentation algorithm applied to many NMT systems and achieving top translation quality in several shared tasks (Denkowski and Neu-big, 2017; Nakazawa et al., 2017).”
• Levenshtein Transformer (2019, methodology): “Data & Evaluation We use three diversified language pairs for MT experiments: WMT’16 Romanian-English (Ro-En) 3 , WMT’14 English-German (En-De) 4 and WAT2017 Small-NMT English-Japanese (En-Ja, Nakazawa et al., 2017) 5 .”
• A Survey of Domain Adaptation for Neural Machine Translation (2018, background): “NMT yields the state-of-the-art translation performance in resource rich scenarios (Bojar et al., 2017; Nakazawa et al., 2017).”
• Overview of the 5th Workshop on Asian Translation (2019, methodology): “Following the success of the previous workshops WAT2014-WAT2018 (Nakazawa et al., 2014, 2015, 2016, 2017, 2018), WAT2019 brings together machine 1One paper was withdrawn post acceptance and hence only 6 papers will be in the proceedings. translation researchers and users to try, evaluate, share and ”
• EDITOR: An Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints (2020, background): “…on three language pairs spanning different language families and data conditions (Table 1): Romanian-English (Ro-En) from WMT16 (Bo-jar et al., 2016), English-German (En-De) from WMT14 (Bojar et al., 2014), and English-Japanese (En-Ja) from WAT2017 Small-NMT Task (Nakazawa et al., 2017).”
• An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks (2020, unknown): “(Nakazawa et al., 2015, 2016, 2017, 2018, 2019).”