40 citations · 170 across the 24 of their papers we have counts for
30 papers
Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation
Yang Zhao, Junnan Zhu, Lu Xiang +4
A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavail…
1st Place Solutions for the UVO Challenge 2022
Jiajun Zhang, Boyu Chen, Zhilong Ji +2
This paper describes the approach we have taken in the challenge. We still adopted the two-stage scheme same as the last champion, that is, detection first and segmentation followe…
Learning Confidence for Transformer-based Neural Machine Translation
Yu Lu, Jiali Zeng, Jiajun Zhang +2
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success. A well-calibrated confidence estimate enables accurate failure p…
Instance-aware Prompt Learning for Language Understanding and Generation
Feihu Jin, Jinliang Lu, Jiajun Zhang +1
Recently, prompt learning has become a new paradigm to utilize pre-trained language models (PLMs) and achieves promising results in downstream tasks with a negligible increase of p…
Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
Jiajun Zhang, Pengyuan Ren, Jianmin Li
Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attri…
Bridging the Modality Gap for Speech-to-Text Translation
Yuchen Liu, Junnan Zhu, Jiajun Zhang +1
End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structur…