35 citations · 78 across the 15 of their papers we have counts for
8 papers · 1 filter
Representation Purification for End-to-End Speech Translation
Chengwei Zhang, Yue Zhou, Rui Zhao +2
Speech-to-text translation (ST) is a cross-modal task that involves converting spoken language into text in a different language. Previous research primarily focused on enhancing s…
Layer-wise Representation Fusion for Compositional Generalization
Yafang Zheng, Lei Lin, Shuangtao Li +6
Existing neural models are demonstrated to struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compositions of seen components…
Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization
Lei Lin, Shuangtao Li, Yafang Zheng +4
Recent studies have shown that sequence-to-sequence (seq2seq) models struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compo…
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
Biao Fu, Minpeng Liao, Kai Fan +4
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than trainin…
Towards Better Document-level Relation Extraction via Iterative Inference
Liang Zhang, Jinsong Su, Yidong Chen +4
Document-level relation extraction (RE) aims to extract the relations between entities from the input document that usually containing many difficultly-predicted entity pairs whose…
Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation
Jiangbin Zheng, Siyuan Li, Cheng Tan +3
Sign Language (SL), as the mother tongue of the deaf community, is a special visual language that most hearing people cannot understand. In recent years, neural Sign Language Trans…
A Token-level Contrastive Framework for Sign Language Translation
Biao Fu, Peigen Ye, Liang Zhang +4
Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people. Recently, researchers have adopted Neural Machine…
Deep Semantic Role Labeling with Self-Attention
Zhixing Tan, Mingxuan Wang, Jun Xie +2
Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end SRL with recurrent neural…