no code implementations • AACL (WAT) 2020 • Zhuoyuan Mao, Yibin Shen, Chenhui Chu, Sadao Kurohashi, Cheqing Jin
This paper describes the Japanese-Chinese Neural Machine Translation (NMT) system submitted by the joint team of Kyoto University and East China Normal University (Kyoto-U+ECNU) to WAT 2020 (Nakazawa et al., 2020).
no code implementations • 11 Jan 2024 • Zhuoyuan Mao, Yen Yu
This article introduces contrastive alignment instructions (AlignInstruct) to address two challenges in machine translation (MT) on large language models (LLMs).
no code implementations • 17 May 2023 • Zhuoyuan Mao, Haiyue Song, Raj Dabre, Chenhui Chu, Sadao Kurohashi
The language-independency of encoded representations within multilingual neural machine translation (MNMT) models is crucial for their generalization ability on zero-shot translation.
no code implementations • 16 May 2023 • Zhuoyuan Mao, Raj Dabre, Qianying Liu, Haiyue Song, Chenhui Chu, Sadao Kurohashi
This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation (ZST).
1 code implementation • 3 May 2023 • Zhen Wan, Fei Cheng, Zhuoyuan Mao, Qianying Liu, Haiyue Song, Jiwei Li, Sadao Kurohashi
In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e. g., GPT-3), they still lag significantly behind fully-supervised baselines (e. g., fine-tuned BERT) in relation extraction (RE).
no code implementations • 16 Feb 2023 • Zhuoyuan Mao, Tetsuji Nakagawa
Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment.
1 code implementation • 29 Nov 2022 • Yibin Shen, Qianying Liu, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi
Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information.
1 code implementation • 21 Oct 2022 • Zhen Wan, Qianying Liu, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi, Jiwei Li
Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models.
1 code implementation • 21 Sep 2022 • Yibin Shen, Qianying Liu, Zhuoyuan Mao, Zhen Wan, Fei Cheng, Sadao Kurohashi
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions.
1 code implementation • 31 May 2022 • Zhuoyuan Mao, Chenhui Chu, Sadao Kurohashi
Massively multilingual sentence representation models, e. g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks.
no code implementations • 18 May 2022 • Zhen Wan, Fei Cheng, Qianying Liu, Zhuoyuan Mao, Haiyue Song, Sadao Kurohashi
Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks.
no code implementations • Findings (NAACL) 2022 • Zhuoyuan Mao, Chenhui Chu, Raj Dabre, Haiyue Song, Zhen Wan, Sadao Kurohashi
Meanwhile, the contrastive objective can implicitly utilize automatically learned word alignment, which has not been explored in many-to-many NMT.
1 code implementation • 20 Jan 2022 • Zhuoyuan Mao, Chenhui Chu, Sadao Kurohashi
In the present study, we propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the source or target language, and English-specific sequence to sequence (ENSS) for language pairs involving English.
1 code implementation • ACL 2021 • Zhuoyuan Mao, Prakhar Gupta, Pei Wang, Chenhui Chu, Martin Jaggi, Sadao Kurohashi
Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks.
no code implementations • ACL 2020 • Haiyue Song, Raj Dabre, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi, Eiichiro Sumita
Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks.
1 code implementation • LREC 2020 • Zhuoyuan Mao, Fabien Cromieres, Raj Dabre, Haiyue Song, Sadao Kurohashi
Monolingual pre-training approaches such as MASS (MAsked Sequence to Sequence) are extremely effective in boosting NMT quality for languages with small parallel corpora.
no code implementations • 23 Jan 2020 • Haiyue Song, Raj Dabre, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi, Eiichiro Sumita
To this end, we propose to exploit monolingual corpora of other languages to complement the scarcity of monolingual corpora for the LOI.