97 citations · 233 across the 33 of their papers we have counts for
29 papers · 1 filter
Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition
Chen Xu, Xiaoqian Liu, Erfeng He +6
In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and…
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Chenglong Wang, Hang Zhou, Yimin Hu +5
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requ…
Learning Evaluation Models from Large Language Models for Sequence Generation
Chenglong Wang, Hang Zhou, Kaiyan Chang +6
Automatic evaluation of sequence generation, traditionally reliant on metrics like BLEU and ROUGE, often fails to capture the semantic accuracy of generated text sequences due to t…
Towards Robust Aspect-based Sentiment Analysis through Non-counterfactual Augmentations
Xinyu Liu, Yan Ding, Kaikai An +4
While state-of-the-art NLP models have demonstrated excellent performance for aspect based sentiment analysis (ABSA), substantial evidence has been presented on their lack of robus…
Recent Advances in Direct Speech-to-text Translation
Chen Xu, Rong Ye, Qianqian Dong +5
Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech…
Modality Adaption or Regularization? A Case Study on End-to-End Speech Translation
Yuchen Han, Chen Xu, Tong Xiao +1
Pre-training and fine-tuning is a paradigm for alleviating the data scarcity problem in end-to-end speech translation (E2E ST). The commonplace "modality gap" between speech and te…
Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Bei Li, Rui Wang, Junliang Guo +7
Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts. While existing…
Augmenting Large Language Model Translators via Translation Memories
Yongyu Mu, Abudurexiti Reheman, Zhiquan Cao +6
Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large langu…
CTC-based Non-autoregressive Speech Translation
Chen Xu, Xiaoqian Liu, Xiaowen Liu +9
Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation a…
Bridging the Granularity Gap for Acoustic Modeling
Chen Xu, Yuhao Zhang, Chengbo Jiao +7
While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies…
TranSFormer: Slow-Fast Transformer for Machine Translation
Bei Li, Yi Jing, Xu Tan +3
Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords…
Multi-Path Transformer is Better: A Case Study on Neural Machine Translation
Ye Lin, Shuhan Zhou, Yanyang Li +3
For years the model performance in machine learning obeyed a power-law relationship with the model size. For the consideration of parameter efficiency, recent studies focus on incr…
Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models
Xinnian Liang, Zefan Zhou, Hui Huang +5
Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and complete…
Prompting Neural Machine Translation with Translation Memories
Abudurexiti Reheman, Tao Zhou, Yingfeng Luo +3
Improving machine translation (MT) systems with translation memories (TMs) is of great interest to practitioners in the MT community. However, previous approaches require either a…
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection
Chenglong Wang, Yi Lu, Yongyu Mu +3
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extra…
EIT: Enhanced Interactive Transformer
Tong Zheng, Bei Li, Huiwen Bao +2
Two principles: the complementary principle and the consensus principle are widely acknowledged in the literature of multi-view learning. However, the current design of multi-head…
Learning Multiscale Transformer Models for Sequence Generation
Bei Li, Tong Zheng, Yi Jing +3
Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language…
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
Bei Li, Quan Du, Tao Zhou +7
Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE). This paper explores a deeper relationship between Transformer and numerical ODE…
On Vision Features in Multimodal Machine Translation
Bei Li, Chuanhao Lv, Zefan Zhou +4
Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision mode…
The NiuTrans System for the WMT21 Efficiency Task
Chenglong Wang, Chi Hu, Yongyu Mu +8
This paper describes the NiuTrans system for the WMT21 translation efficiency task (http://statmt.org/wmt21/efficiency-task.html). Following last year's work, we explore various te…
The NiuTrans End-to-End Speech Translation System for IWSLT 2021 Offline Task
Chen Xu, Xiaoqian Liu, Xiaowen Liu +4
This paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text dir…
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Chen Xu, Bojie Hu, Yanyang Li +5
Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Autom…
Towards Fully 8-bit Integer Inference for the Transformer Model
Ye Lin, Yanyang Li, Tengbo Liu +3
8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently. On the other hand, previous sy…
Neural Machine Translation with Joint Representation
Yanyang Li, Qiang Wang, Tong Xiao +2
Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units,…