Kenji's Home Page
Kenji Imamura (今村 賢治)
A researcher of natural language processing.
My research interests include: 1) machine translation, 2) NLP using neural networks, 3) natural language generation, 4) natural language analysis (dependency parsing, predicate-argument structure analysis).
Recent Publications
2023
NAIST-NICT WMT’23 General MT Task Submission
Hiroyuki Deguchi, Kenji Imamura, Yuto Nishida, Yusuke Sakai, Justin Vasselli and Taro Watanabe.
The 8th Conference on Machine Translation (WMT23), pp. 110-118, Dec. 2023.
Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model
Kenji Imamura, Masao Utiyama, and Eiichiro Sumita.
Machine Translation Summit XIX (MT Summit 2023), pp. 348-359, Sep. 2023.
A Study of Pivot Translation between Non-English Languages Using Multilingual Models
Subword Addtion to a SentencePiece Tokenizer for Multilingual Pretrained Models
in Japanese. 「多言語事前学習モデルのためのSentencePieceトークナイザーへのサブワード追加」
Kenji Imamura and Eiichiro Sumita.
The 29th Annual Meeting of Assoc. for Natural Language Processing, pp. 1474-1479, Mar. 2023.
[paper / bib / sample code]
Construction of GCP Simultaneous Corpus
2022
NAIST-NICT-TIT WMT22 General MT Task Submission
Hiroyuki Deguchi, Kenji Imamura, Masahiro Kaneko, Yuto Nishida, Yusuke Sakai, Justin Vasselli, Huy Hien Vu, Taro Watanabe
The 7th Conference on Machine Translation (WMT22), pp. 244-250, Dec. 2022.
Extending the Subwording Model of Multilingual Pretrained Models for New Languages
Kenji Imamura and Eiichiro Sumita
arXiv e-Print 2211.15965, Nov. 2022.
Speeding up of Multilingual Pretrained Machine Translation by Vocabulary Selection
in Japanese. 「多言語事前訓練機械翻訳の語彙選択による高速化」
Kenji Imamura
Japio YEAR BOOK 2022, pp. 326-328, Nov. 2022.
A Survey of Machine Translation Technologies for Machine Translation on Patent Documents
in Japanese. 「特許機械翻訳の課題解決に向けた機械翻訳技術解説」
Kenji Imamura, Hiroshi Echizen-ya, Terumasa Ehara, Isao Goto, Katsuhito Sudoh, Satoshi Sonoo, Takashi Tsunakawa, Toshiaki Nakazawa, Takashi Ninomiya, Xiangli Wang
Journal of Natural Language Processing, Vol.29, No.3, pp. 925-985, Sep. 2022.
[paper (J-stage) / bib]
2021
Language Expansion of a Pretrained Model and its Effects
in Japanese. 「事前訓練モデルの言語拡張とその効果」
Kenji Imamura and Eiichiro Sumita
Japio YEAR BOOK 2021, pp. 302-305, Nov. 2021.
NICT-2 Translation System at WAT-2021: Applying a Pretrained Multilingual Encoder-Decoder Model to Low-resource Language Pairs
Kenji Imamura and Eiichiro Sumita
The 8th Workshop on Asian Translation (WAT-2021) in ACL-IJCNLP 2021, pp. 90-95, Aug. 2021.
A Study of Speed-up in Neural Machine Translation Combined with Knowledge Distillation.
in Japanese. 「知識蒸留によるニューラル機械翻訳の高速化検討」
Kenji Imamura.
The 27th Annual Meeting of Assoc. for Natural Language Processing, 123-127, Mar. 2021.
[paper (J-stage) / bib / appendix ]
2020
Transformer-based Double-token Bidirectional Autoregressive Decoding in Neural Machine Translation
Kenji Imamura and Eiichiro Sumita.
The 7th Workshop on Asian Translation (WAT-2020) in AACL-IJCNLP 2020, pp. 50-57, Dec. 2020.
Improvement of Neural Machine Translation that Uses Non-autoregressive Decoding
in Japanese. 「非自己回帰デコーディング型ニューラル機械翻訳の改善」
Kenji Imamura.
Japio YEAR BOOK 2020, pp. 296-299, Nov. 2020.
Neural Machine Translation Using Multiple Back-translation Generated by Sampling
in Japanese. 「サンプリング生成に基づく複数逆翻訳を用いたニューラル機械翻訳」
Kenji Imamura, Atsushi Fujita, and Eiichiro Sumita.
Transactions of the Japanese Society for Artificial Intelligence, Vol.35, Issue 3, pp. A-JA9_1-9, May 2020.
[paper (J-STAGE) / bib]
Language Translation
2019
Recycling a Pre-trained BERT Encoder for Neural Machine Translation
Kenji Imamura and Eiichiro Sumita.
The 3rd Workshop on Neural Generation and Translation (WNGT 2019) in EMNLP-IJCNLP 2019, pp. 23-31, November 2019.
Long Warm-up and Self-Training: Training Strategies of NICT-2 NMT System at WAT-2019
Kenji Imamura and Eiichiro Sumita.
The 6th Workshop on Asian Translation (WAT 2019) in EMNLP-IJCNLP 2019, pp. 141-145, November 2019.
Neural Machine Translation that Recycles Pre-trained BERT Encoder
in Japanese. 「事前訓練済みBERTエンコーダーを再利用したニューラル機械翻訳」
Kenji Imamura and Eiichiro Sumita.
IPSJ SIG Technical Report 2019-NL-241, No.1, pp.1-8, August 2019.
IPSJ SIG-NL No.241 Excellect Research Award
Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation
Aizhan Imankulova, Raj Dabre, Atsushi Fujita, and Kenji Imamura.
Machine Translation Summit XVII, Volume 1: Research Track, pp.128-139, August 2019.
[paper (arXiv) / bib]
Usage of Long Context in Dialogue Translation
in Japanese. 「対話翻訳における長距離文脈の利用」
Kenji Imamura and Eiichiro Sumita.
The 25th Annual Meeting of Assoc. for Natural Language Processing, pp.550-553, March 2019.
[paper (J-stage) / bib]
Recent Pictures
StartBucks
Post Office
Bank
Near Ise-Jingu Shrine, Aug. 2024
Deerlet 2024
May, 2024