no code implementations • EMNLP 2021 • Zifa Gan, Hongfei Xu, Hongying Zan
By contrast, Curriculum Learning (CL) utilizes training data differently during training and has shown its effectiveness in improving both performance and training efficiency in many other NLP tasks.
no code implementations • COLING 2022 • Wenjie Hao, Hongfei Xu, Deyi Xiong, Hongying Zan, Lingling Mu
Paraphrasing, i. e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP).
no code implementations • 23 Aug 2023 • Songhua Yang, Chenghao Zhang, Hongfei Xu, Yuxiang Jia
However, existing research falls short in tackling the more complex Chinese BEN task, especially in the few-shot scenario with limited medical data, and the vast potential of the external medical knowledge base has yet to be fully harnessed.
1 code implementation • 7 Aug 2023 • Songhua Yang, Hanjie Zhao, Senbin Zhu, Guangyu Zhou, Hongfei Xu, Yuxiang Jia, Hongying Zan
Recent advances in Large Language Models (LLMs) have achieved remarkable breakthroughs in understanding and responding to user intents.
no code implementations • 24 Dec 2022 • Wenjie Hao, Hongfei Xu, Lingling Mu, Hongying Zan
In this paper, we study the use of deep Transformer translation model for the CCMT 2022 Chinese-Thai low-resource machine translation task.
no code implementations • 7 Nov 2022 • Tengxun Zhang, Hongfei Xu, Josef van Genabith, Deyi Xiong, Hongying Zan
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction.
no code implementations • ACL 2021 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Meng Zhang
This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this.
no code implementations • ACL 2021 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong
In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality.
no code implementations • Findings (EMNLP) 2021 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong
The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily.
no code implementations • 13 Jul 2020 • Hongfei Xu, Yang song, Qiuhui Liu, Josef van Genabith, Deyi Xiong
Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance.
no code implementations • ACL 2020 • Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu, Jingyi Zhang
Considering that modeling phrases instead of words has significantly improved the Statistical Machine Translation (SMT) approach through the use of larger translation blocks ("phrases") and its reordering ability, modeling NMT at phrase level is an intuitive proposal to help the model capture long-distance relationships.
no code implementations • ACL 2020 • Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu
We propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate.
no code implementations • NAACL 2021 • Hongfei Xu, Josef van Genabith, Qiuhui Liu, Deyi Xiong
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches.
no code implementations • ACL 2020 • Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Jingyi Zhang
In this paper, we first empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers.
no code implementations • COLING 2020 • Santanu Pal, Hongfei Xu, Nico Herbig, Sudip Kumar Naskar, Antonio Krueger, Josef van Genabith
In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input.
no code implementations • WS 2019 • Hongfei Xu, Qiuhui Liu, Josef van Genabith
In this paper, we describe our submission to the English-German APE shared task at WMT 2019.
no code implementations • WS 2019 • Santanu Pal, Hongfei Xu, Nico Herbig, Antonio Kr{\"u}ger, Josef van Genabith
In this paper we present an English{--}German Automatic Post-Editing (APE) system called transference, submitted to the APE Task organized at WMT 2019.
2 code implementations • 18 Mar 2019 • Hongfei Xu, Qiuhui Liu
The Transformer translation model is easier to parallelize and provides better performance compared to recurrent seq2seq models, which makes it popular among industry and research community.