Search Results - "Li, Liangyou"

Adversarial parameter defense by multi-step risk minimization by Zhang, Zhiyuan, Luo, Ruixuan, Ren, Xuancheng, Su, Qi, Li, Liangyou, Sun, Xu

“…Previous studies demonstrate DNNs’ vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition,…”
Get full text

Bilingual phrase induction with local hard negative sampling by Cao, Hailong, Miao, Hualin, Wang, Weixuan, Li, Liangyou, Peng, Wei, Zhao, Tiejun

“…Abstract Bilingual lexicon induction focuses on learning word translation pairs, also known as bitexts, from monolingual corpora by establishing a mapping…”
Get full text

An Optimized Video-Based Traffic Congestion Monitoring System by Fei Zhu, Liangyou Li

“…Traffic congestion monitoring is being more and important with the enlarging of urban scale and increasing number of vehicles. Video-based traffic congestion…”
Get full text

Combining translation memories and statistical machine translation using sparse features by Li, Liangyou, Escartín, Carla Parra, Way, Andy, Liu, Qun

“…The combination of translation memories (TMs) and statistical machine translation (SMT) has been demonstrated to be beneficial. In this paper, we present a…”
Get full text

Combining Translation Memories and Syntax-Based: SMT Experiments with Real Industrial Data by Li, Liangyou, Escartín, Carla Parra, Liu, Qun

“…One major drawback of using Translation Memories (TMs) in phrase-based Machine Translation (MT) is that only continuous phrases are considered. In contrast,…”
Get full text

AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation by Zeng, Xingshan, Li, Liangyou, Liu, Qun

“…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…”
Get full text

Triangular Transfer: Freezing the Pivot for Triangular Machine Translation by Zhang, Meng, Li, Liangyou, Liu, Qun

“…Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both…”
Get full text

End-to-end Training and Decoding for Pivot-based Cascaded Translation Model by Cheng, Hao, Zhang, Meng, Li, Liangyou, Liu, Qun, Zhang, Zhihua

“…Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and…”
Get full text

RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer by Zeng, Xingshan, Li, Liangyou, Liu, Qun

“…End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in…”
Get full text

Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021 by Zeng, Xingshan, Li, Liangyou, Liu, Qun

“…This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified…”
Get full text

SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme by Sun, Yusen, Li, Liangyou, Liu, Qun, Yeung, Dit-Yan

“…Although lyrics generation has achieved significant progress in recent years, it has limited practical applications because the generated lyrics cannot be…”
Get full text

Dependency Graph-to-String Statistical Machine Translation by Li, Liangyou, Way, Andy, Liu, Qun

“…We present graph-based translation models which translate source graphs into target strings. Source graphs are constructed from dependency trees with extra…”
Get full text

Mitigating Large Language Model Hallucination with Faithful Finetuning by Hu, Minda, He, Bowei, Wang, Yufei, Li, Liangyou, Ma, Chen, King, Irwin

“…Large language models (LLMs) have demonstrated remarkable performance on various natural language processing tasks. However, they are prone to generating…”
Get full text

Future-Guided Incremental Transformer for Simultaneous Translation by Zhang, Shaolei, Feng, Yang, Li, Liangyou

“…Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k…”
Get full text

Analysis and Compensation of Reverse Clearance of Feed Axis of Pipe Bender by Wu, Yiqing, Li, Bing, Li, Liangyou, Shen, Yang, Zhang, Qingzhu, Wang, Ting

“…The reverse clearance is a critical factor affecting the accuracy of the feed axis in pipe bending machines, necessitating thorough investigation to enhance…”
Get full text

Automatic Programming Method and System of Multi-Axis CNC Pipe Bender by Zhang, Boyang, Wei, Yulan, Li, Liangyou, Peng, Jiwen, Han, Hongtao, Li, Bing

“…The all-electric CNC pipe bender can be used to replace the hydraulic CNC pipe bender to bend pipe fittings. The user inputs the required bending parameters…”
Get full text

FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models by Guo, Yinpeng, Li, Liangyou, Jiang, Xin, Liu, Qun

“…Cross-lingual transfer (CLT) is of various applications. However, labeled cross-lingual corpus is expensive or even inaccessible, especially in the fields…”
Get full text

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis by Wang, Zezhong, Zeng, Xingshan, Liu, Weiwen, Li, Liangyou, Wang, Yasheng, Shang, Lifeng, Jiang, Xin, Liu, Qun, Wong, Kam-Fai

“…Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being…”
Get full text

Universal Conditional Masked Language Pre-training for Neural Machine Translation by Li, Pengfei, Li, Liangyou, Zhang, Meng, Wu, Minghao, Liu, Qun

“…Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT). Different from prior works where pre-trained models…”
Get full text

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization by Jiang, Yuxin, Huang, Bo, Wang, Yufei, Zeng, Xingshan, Li, Liangyou, Wang, Yasheng, Jiang, Xin, Shang, Lifeng, Tang, Ruiming, Wang, Wei

“…Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired…”
Get full text