19 citations · 42 across the 13 of their papers we have counts for
14 papers
Tgea: An error-annotated dataset and benchmark tasks for text generation from pretrained language models
Jie He, Bo Peng, Yi Liao +2
In order to deeply understand the capability of pretrained language models in text generation and conduct a diagnostic evaluation, we propose TGEA, an error-annotated dataset with…
Evaluating the Efficacy of Length-Controllable Machine Translation
Hao Cheng, Meng Zhang, Weixuan Wang +3
Length-controllable machine translation is a type of constrained translation. It aims to contain the original meaning as much as possible while controlling the length of the transl…
End-to-end Training and Decoding for Pivot-based Cascaded Translation Model
Hao Cheng, Meng Zhang, Liangyou Li +2
Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and pivot-target, are trained ind…
Learning Homographic Disambiguation Representation for Neural Machine Translation
Weixuan Wang, Wei Peng, Qun Liu
Homographs, words with the same spelling but different meanings, remain challenging in Neural Machine Translation (NMT). While recent works leverage various word embedding approach…
AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation
Xingshan Zeng, Liangyou Li, Qun Liu
To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important tech…
SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme
Yusen Sun, Liangyou Li, Qun Liu +1
Although lyrics generation has achieved significant progress in recent years, it has limited practical applications because the generated lyrics cannot be performed without composi…
Triangular Transfer: Freezing the Pivot for Triangular Machine Translation
Meng Zhang, Liangyou Li, Qun Liu
Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both languages have abundant…
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
Minghao Wu, Yitong Li, Meng Zhang +3
Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in re…
KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs
Yinquan Lu, Haonan Lu, Guirong Fu +1
Incorporating factual knowledge into pre-trained language models (PLM) such as BERT is an emerging trend in recent NLP studies. However, most of the existing methods combine the ex…
Dynamic Multi-Branch Layers for On-Device Neural Machine Translation
Zhixing Tan, Zeyuan Yang, Meng Zhang +3
With the rapid development of artificial intelligence (AI), there is a trend in moving AI applications, such as neural machine translation (NMT), from cloud to mobile devices. Cons…
ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
Peyman Passban, Yimeng Wu, Mehdi Rezagholizadeh +1
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The…
Revisiting Robust Neural Machine Translation: A Transformer Case Study
Peyman Passban, Puneeth S. M. Saladi, Qun Liu
Transformers (Vaswani et al., 2017) have brought a remarkable improvement in the performance of neural machine translation (NMT) systems but they could be surprisingly vulnerable t…
Document Graph for Neural Machine Translation
Mingzhou Xu, Liangyou Li, Derek. F. Wong +2
Previous works have shown that contextual information can improve the performance of neural machine translation (NMT). However, most existing document-level NMT methods only consid…
Improve the Evaluation of Fluency Using Entropy for Machine Translation Evaluation Metrics
Hui Yu, Xiaofeng Wu, Wenbin Jiang +2
The widely-used automatic evaluation metrics cannot adequately reflect the fluency of the translations. The n-gram-based metrics, like BLEU, limit the maximum length of matched fra…