2 code implementations • 8 Mar 2024 • Chengyang Zhang, Yong Zhang, Qitan Shao, Jiangtao Feng, Bo Li, Yisheng Lv, Xinglin Piao, BaoCai Yin
The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations.
no code implementations • 18 Dec 2023 • Jun Zhang, Shuyang Jiang, Jiangtao Feng, Lin Zheng, Lingpeng Kong
Given that orthogonal memory compresses global information, we further dissect the context to amplify fine-grained local information.
1 code implementation • 14 Oct 2023 • Shuyang Jiang, Jun Zhang, Jiangtao Feng, Lin Zheng, Lingpeng Kong
Furthermore, we marry AMLP with popular NAR models, deriving a highly efficient NAR-AMLP architecture with linear time and space complexity.
1 code implementation • 9 Oct 2023 • Shansan Gong, Mukai Li, Jiangtao Feng, Zhiyong Wu, Lingpeng Kong
Diffusion models have gained prominence in generating high-quality sequences of text.
no code implementations • 23 May 2023 • Chenxin An, Jiangtao Feng, Fei Huang, Xipeng Qiu, Lingpeng Kong
In this paper, we propose to ease the difficulty of modality learning via sampling from the model distribution instead of the data distribution.
3 code implementations • 6 Mar 2023 • Zhenyu Wu, Yaoxiang Wang, Jiacheng Ye, Jiangtao Feng, Jingjing Xu, Yu Qiao, Zhiyong Wu
However, the implementation of ICL is sophisticated due to the diverse retrieval and inference methods involved, as well as the varying pre-processing requirements for different models, datasets, and tasks.
1 code implementation • 11 Feb 2023 • Jiacheng Ye, Zhiyong Wu, Jiangtao Feng, Tao Yu, Lingpeng Kong
The performance of ICL is highly dominated by the quality of the selected in-context examples.
1 code implementation • 9 Feb 2023 • Mukai Li, Shansan Gong, Jiangtao Feng, Yiheng Xu, Jun Zhang, Zhiyong Wu, Lingpeng Kong
Based on EVALM, we scale up the size of examples efficiently in both instruction tuning and in-context learning to explore the boundary of the benefits from more annotated data.
2 code implementations • 22 Oct 2022 • Jiacheng Ye, Jiahui Gao, Jiangtao Feng, Zhiyong Wu, Tao Yu, Lingpeng Kong
To improve the quality of dataset synthesis, we propose a progressive zero-shot dataset generation framework, ProGen, which leverages the feedback from the task-specific model to guide the generation of new training data via in-context examples.
1 code implementation • 17 Oct 2022 • Shansan Gong, Mukai Li, Jiangtao Feng, Zhiyong Wu, Lingpeng Kong
Bringing together theoretical analysis and empirical evidence, we demonstrate the great potential of diffusion models in complex conditional language generation tasks.
1 code implementation • 14 Oct 2022 • Jun Zhang, Shuyang Jiang, Jiangtao Feng, Lin Zheng, Lingpeng Kong
In this paper, we propose Comprehensive Attention Benchmark (CAB) under a fine-grained attention taxonomy with four distinguishable attention patterns, namely, noncausal self, causal self, noncausal cross, and causal cross attentions.
1 code implementation • 7 Oct 2022 • Jiangtao Feng, Yi Zhou, Jun Zhang, Xian Qian, Liwei Wu, Zhexi Zhang, Yanming Liu, Mingxuan Wang, Lei LI, Hao Zhou
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.
2 code implementations • 29 May 2022 • Chenxin An, Jiangtao Feng, Kai Lv, Lingpeng Kong, Xipeng Qiu, Xuanjing Huang
We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation.
3 code implementations • 16 Feb 2022 • Jiacheng Ye, Jiahui Gao, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, Lingpeng Kong
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs).
1 code implementation • EMNLP 2021 • Dongyu Ru, Changzhi Sun, Jiangtao Feng, Lin Qiu, Hao Zhou, Weinan Zhang, Yong Yu, Lei LI
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #21 on Relation Extraction on DocRED
no code implementations • WMT (EMNLP) 2021 • Lihua Qian, Yi Zhou, Zaixiang Zheng, Yaoming Zhu, Zehui Lin, Jiangtao Feng, Shanbo Cheng, Lei LI, Mingxuan Wang, Hao Zhou
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
1 code implementation • Findings (EMNLP) 2021 • Yaoming Zhu, Jiangtao Feng, Chengqi Zhao, Mingxuan Wang, Lei LI
Developing a unified multilingual model has long been a pursuit for machine translation.
no code implementations • 22 Mar 2021 • Liping Yuan, Jiangtao Feng, Xiaoqing Zheng, Xuanjing Huang
The key idea is that at each time step, the network takes as input a ``bundle'' of similar words predicted at the previous step instead of a single ground truth.
1 code implementation • EMNLP 2020 • Zehui Lin, Xiao Pan, Mingxuan Wang, Xipeng Qiu, Jiangtao Feng, Hao Zhou, Lei LI
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs?
Ranked #3 on Machine Translation on WMT2014 English-French (using extra training data)
no code implementations • Findings of the Association for Computational Linguistics 2020 • Dongyu Ru, Jiangtao Feng, Lin Qiu, Hao Zhou, Mingxuan Wang, Wei-Nan Zhang, Yong Yu, Lei LI
We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently.
no code implementations • 25 Nov 2019 • Yu Bao, Hao Zhou, Jiangtao Feng, Mingxuan Wang, Shu-Jian Huang, Jia-Jun Chen, Lei LI
Non-autoregressive models are promising on various text generation tasks.
2 code implementations • 24 Oct 2019 • An Yan, Xin Eric Wang, Jiangtao Feng, Lei LI, William Yang Wang
Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics.
no code implementations • 25 Sep 2019 • Yu Bao, Hao Zhou, Jiangtao Feng, Mingxuan Wang, ShuJian Huang, Jiajun Chen, Lei LI
However, position modeling of output words is an essential problem in non-autoregressive text generation.
no code implementations • 6 Nov 2018 • Jiangtao Feng, Lingpeng Kong, Po-Sen Huang, Chong Wang, Da Huang, Jiayuan Mao, Kan Qiao, Dengyong Zhou
We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018).