invigorating
发表于 2025-3-21 18:03:21
书目名称Machine Translation影响因子(影响力)<br> http://impactfactor.cn/if/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation影响因子(影响力)学科排名<br> http://impactfactor.cn/ifr/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation网络公开度<br> http://impactfactor.cn/at/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation网络公开度学科排名<br> http://impactfactor.cn/atr/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation被引频次<br> http://impactfactor.cn/tc/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation被引频次学科排名<br> http://impactfactor.cn/tcr/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation年度引用<br> http://impactfactor.cn/ii/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation年度引用学科排名<br> http://impactfactor.cn/iir/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation读者反馈<br> http://impactfactor.cn/5y/?ISSN=BK0620773<br><br> <br><br>书目名称Machine Translation读者反馈学科排名<br> http://impactfactor.cn/5yr/?ISSN=BK0620773<br><br> <br><br>
暖昧关系
发表于 2025-3-21 21:36:20
CCMT 2022 Translation Quality Estimation Task, found that pre-training the predictor with the semantic textual similarity (STS) task in the parallel corpus and using augmented training data constructed by different machine translation (MT) engines can improve the prediction effect of the Human-targeted Translation Edit Rate (HTER) in both Chinese-English and English-Chinese tasks.
装勇敢地做
发表于 2025-3-22 01:23:40
http://reply.papertrans.cn/63/6208/620773/620773_3.png
爵士乐
发表于 2025-3-22 05:29:59
http://reply.papertrans.cn/63/6208/620773/620773_4.png
先行
发表于 2025-3-22 09:05:07
,Multi-strategy Enhanced Neural Machine Translation for Chinese Minority Languages,d Ensemble. Our enhancement experiments have proved the effectiveness of above-mentioned strategies. We submit enhanced systems as primary systems for the three tracks. In addition, we train contrast models using additional bilingual data and submit results generated by these contrast models.
Arthropathy
发表于 2025-3-22 13:44:00
,An Improved Multi-task Approach to Pre-trained Model Based MT Quality Estimation,r model. We show that the post-editing sub-task is much more in-formative and the mBART is superior to other pre-trained models. Experiments on WMT2021 English-German and English-Chinese QE datasets showed that the proposed method achieves 1.2%–2.1% improvements in the strong sentence-level QE baseline.
卡死偷电
发表于 2025-3-22 20:17:30
http://reply.papertrans.cn/63/6208/620773/620773_7.png
值得赞赏
发表于 2025-3-23 01:10:57
,Effective Data Augmentation Methods for CCMT 2022,ormer model with several effective data augmentation strategies which are adopted to improve the quality of translation. Experiments show that data augmentation methods have a good impact on the baseline system and aim to enhance the robustness of the model.
IST
发表于 2025-3-23 04:04:15
,NJUNLP’s Submission for CCMT 2022 Quality Estimation Task,hich achieves outstanding success in many NLP tasks in order to improve performance. With the purpose of better utilizing parallel data, several types of pseudo data are employed in our method as well. In addition, we also ensemble several models to promote the final results.
挑剔为人
发表于 2025-3-23 07:05:29
http://reply.papertrans.cn/63/6208/620773/620773_10.png