Следене
Jin Sakuma
Jin Sakuma
Потвърден имейл адрес: tkl.iis.u-tokyo.ac.jp - Начална страница
Заглавие
Позовавания
Позовавания
Година
Wikipedia2Vec: An efficient toolkit for learning and visualizing the embeddings of words and entities from Wikipedia
I Yamada, A Asai, J Sakuma, H Shindo, H Takeda, Y Takefuji, ...
arXiv preprint arXiv:1812.06280, 2018
2002018
A bag of useful tricks for practical neural machine translation: Embedding layer initialization and large batch size
M Neishi, J Sakuma, S Tohda, S Ishiwatari, N Yoshinaga, M Toyoda
Proceedings of the 4th Workshop on Asian Translation (WAT2017), 99-109, 2017
652017
Vocabulary adaptation for domain adaptation in neural machine translation
S Sato, J Sakuma, N Yoshinaga, M Toyoda, M Kitsuregawa
Findings of the Association for Computational Linguistics: EMNLP 2020, 4269-4279, 2020
322020
Response timing estimation for spoken dialog systems based on syntactic completeness prediction
J Sakuma, S Fujie, T Kobayashi
2022 IEEE Spoken Language Technology Workshop (SLT), 369-374, 2023
72023
MLP-based architecture with variable length input for automatic speech recognition
J Sakuma, T Komatsu, R Scheibler
72021
Timing Generating Networks: Neural Network Based Precise Turn-Taking Timing Prediction in Multiparty Conversation.
S Fujie, H Katayama, J Sakuma, T Kobayashi
Interspeech, 3226-3230, 2021
62021
Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia. ArXiv 2020
I Yamada, A Asai, J Sakuma, H Shindo, H Takeda, Y Takefuji, ...
arXiv preprint arXiv:1812.06280, 0
6
MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
J Sakuma, T Komatsu, R Scheibler
arXiv preprint arXiv:2202.08456, 2022
42022
Response Timing Estimation for Spoken Dialog System using Dialog Act Estimation.
J Sakuma, S Fujie, T Kobayashi
INTERSPEECH, 4486-4490, 2022
32022
Vocabulary adaptation for distant domain adaptation in neural machine translation
S Sato, J Sakuma, N Yoshinaga, M Toyoda, M Kitsuregawa
arXiv preprint arXiv:2004.14821, 2020
22020
Conversation-oriented asr with multi-look-ahead cbs architecture
H Zhao, S Fujie, T Ogawa, J Sakuma, Y Kida, T Kobayashi
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
12023
Multilingual model using cross-task embedding projection
J Sakuma, N Yoshinaga
Proceedings of the 23rd Conference on Computational Natural Language …, 2019
12019
ニューラル機械翻訳における埋め込み層の教師なし事前学習
根石将人, 佐久間仁, 遠田哲史, 石渡祥之佑, 吉永直樹, 豊田正史
研究報告自然言語処理 (NL) 2017 (1), 1-8, 2017
12017
Improving the response timing estimation for spoken dialogue systems by reducing the effect of speech recognition delay
J Sakuma, S Fujie, H Zhao, T Kobayashi
Proceedings of the Annual Conference of the International Speech …, 2023
2023
Unsupervised Cross-lingual Word Embeddings Based on Subword Alignment
J Sakuma, N Yoshinaga
EasyChair, 2019
2019
単語の表層類似性を用いた多言語単語分散表現の教師なし学習手法
佐久間仁, 吉永直樹
研究報告自然言語処理 (NL) 2017 (14), 1-7, 2017
2017
Cross-lingual transfer learning considering word order difference
H Zhan, J Sakuma, N Yoshinaga, M Toyoda
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–17