no code implementations • WMT (EMNLP) 2020 • Tingxun Shi, Shiyu Zhao, Xiaopu Li, Xiaoxue Wang, Qian Zhang, Di Ai, Dawei Dang, Xue Zhengshan, Jie Hao
In this paper we demonstrate our (OPPO’s) machine translation systems for the WMT20 Shared Task on News Translation for all the 22 language pairs.
no code implementations • WMT (EMNLP) 2021 • Shiyu Zhao, Xiaopu Li, Minghui Wu, Jie Hao
This paper describes Mininglamp neural machine translation systems of the WMT2021 news translation tasks.
no code implementations • NAACL 2022 • Dingcheng Li, Zheng Chen, Eunah Cho, Jie Hao, Xiaohu Liu, Fan Xing, Chenlei Guo, Yang Liu
Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting.
no code implementations • EMNLP 2021 • Jie Hao, Linfeng Song, LiWei Wang, Kun Xu, Zhaopeng Tu, Dong Yu
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
no code implementations • EMNLP (IWSLT) 2019 • Xiaopu Li, Zhengshan Xue, Jie Hao
On the devsets of IWSLT 2019, the BLEU of our system reaches 19. 94.
no code implementations • EMNLP (NLP4ConvAI) 2021 • Eunah Cho, Ziyan Jiang, Jie Hao, Zheng Chen, Saurabh Gupta, Xing Fan, Chenlei Guo
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect.
no code implementations • EMNLP 2021 • Zhuoyi Wang, Saurabh Gupta, Jie Hao, Xing Fan, Dingcheng Li, Alexander Hanbo Li, Chenlei Guo
Rephrase detection is used to identify the rephrases and has long been treated as a task with pairwise input, which does not fully utilize the contextual information (e. g. users’ implicit feedback).
1 code implementation • 17 Jan 2024 • Jie Hao, Xiaochuan Gong, Mingrui Liu
When the upper-level problem is nonconvex and unbounded smooth, and the lower-level problem is strongly convex, we prove that our algorithm requires $\widetilde{\mathcal{O}}(1/\epsilon^4)$ iterations to find an $\epsilon$-stationary point in the stochastic setting, where each iteration involves calling a stochastic gradient or Hessian-vector product oracle.
no code implementations • 11 Jul 2023 • Rixin Wu, Ran Wang, Jie Hao, Qiang Wu, Ping Wang
Due to shortage of water resources and increasing water demands, the joint operation of multireservoir systems for balancing power generation, ecological protection, and the residential water supply has become a critical issue in hydropower management.
no code implementations • 22 Oct 2022 • Niranjan Uma Naresh, Ziyan Jiang, Ankit, Sungjin Lee, Jie Hao, Xing Fan, Chenlei Guo
Conversational understanding is an integral part of modern intelligent devices.
2 code implementations • 24 Jul 2022 • Xiaoming Ren, Huifeng Zhu, Liuwei Wei, Minghui Wu, Jie Hao
In this work, we believe that the output information of each block in the encoder and decoder is not completely inclusive, in other words, their output information may be complementary.
Ranked #4 on Speech Recognition on AISHELL-1
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 29 Dec 2020 • Jie Hao, Linfeng Song, LiWei Wang, Kun Xu, Zhaopeng Tu, Dong Yu
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
no code implementations • SEMEVAL 2020 • Yili Ma, Liang Zhao, Jie Hao
In this paper, we present an approach for sentiment analysis in code-mixed language on twitter defined in SemEval-2020 Task 9.
no code implementations • WS 2020 • Qian Zhang, Xiaopu Li, Dawei Dang, Tingxun Shi, Di Ai, Zhengshan Xue, Jie Hao
In this paper, we demonstrate our machine translation system applied for the Chinese-Japanese bidirectional translation task (aka.
no code implementations • IJCNLP 2019 • Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information.
no code implementations • IJCNLP 2019 • Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu
Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work.
no code implementations • NAACL 2019 • Jie Hao, Xing Wang, Baosong Yang, Long-Yue Wang, Jinfeng Zhang, Zhaopeng Tu
In addition to the standard recurrent neural network, we introduce a novel attentive recurrent network to leverage the strengths of both attention and recurrent networks.
no code implementations • 1 May 2018 • Bo Zhang, Wei Li, Jie Hao, Xiao-Li Li, Meng Zhang
The layers between the source and target feature extractor are partially untied during the training stage to take both training efficiency and domain adaptation into consideration.