SLP-P36.10
Fovea Transformer: Efficient Long-Context Modeling with Structured Fine-to-Coarse Attention
Ziwei He, Jian Yuan, Le Zhou, Jingwen Leng, Bo Jiang, Shanghai Jiao Tong University, China
Session:
SLP-P36: machine learning methods for language Poster
Track:
Speech and Language Processing
Location:
Poster Zone 3C
Poster Board PZ-3C.10
Poster Board PZ-3C.10
Presentation Time:
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)
Session Co-Chairs:
Yi Su, Apple Inc and Yun Tang, Samsung USA
Session SLP-P36
SLP-P36.1: DYNAMIC DATA SAMPLER FOR CROSS-LANGUAGE TRANSFER LEARNING IN LARGE LANGUAGE MODELS
Yudong Li, Shenzhen University, China; Yuhao Feng, Tencent AI Lab, China; Wen Zhou, Wuhan University, China; Zhe Zhao, Tencent AI Lab, China; Linlin Shen, Shenzhen University, China; Cheng Hou, Tencent AI Lab, China; Xianxu Hou, Shenzhen University, China
SLP-P36.2: CONTRASTIVE LEARNING WITH HIGH-QUALITY AND LOW-QUALITY AUGMENTED DATA FOR QUERY-FOCUSED SUMMARIZATION
Shaoyao Huang, Ziqiang Cao, Luozheng Qin, Jun Gao, Soochow University, China; Jun Zhang, Changping Laboratory, China
SLP-P36.3: SIGNIFICANT ASR ERROR DETECTION FOR CONVERSATIONAL VOICE ASSISTANTS
John Harvill, University of Illinois at Urbana-Champaign, Amazon Alexa AI, United States of America; Rinat Khaziev, Scarlett Li, Randy Cogill, Lidan Wang, Gopinath Chennupati, Hari Thadakamalla, Amazon, United States of America
SLP-P36.4: USING CLUSTERING TO IMPROVE THE PERFORMANCE OF FEW-SHOT LEARNING
Yanan Zhang, Chaofan Wu, Rongkun Shi, Yiying Zhang, Tianjin University of Science and Technology, China
SLP-P36.5: A FEDERATED GRAPH TO EMBEDDING APPROACH FOR KNOWLEDGE GRAPH COMPLETION
Hongliang Sun, Xiaofeng Bi, Dianbo Sui, Zhiying Tu, Harbin Institute of Technology, Weihai, China
SLP-P36.6: Unsupervised Multiple Choices Question Answering via Universal Corpus
Qin Zhang, Hao Ge, Xiaojun Chen, Shenzhen University, China; Meng Fang, University of Liverpool, United Kingdom of Great Britain and Northern Ireland
SLP-P36.7: FINE-TUNING SELF-SUPERVISED MODELS FOR LANGUAGE IDENTIFICATION USING ORTHONORMAL CONSTRAINT
Amrutha Prasad, Idiap Research Institute, Switzerland; Andrés Carofilis, University of León, Spain; Geoffroy Vanderreydt, IDLab, Ghent University, Belgium; Driss Khalil, Srikanth Madikeri, Petr Motlicek, Idiap Research Institute, Switzerland; Christof Schuepbach, Armasuisse Science and Technology, Switzerland
SLP-P36.8: SNAPSHOT PROMPT ENSEMBLE FOR PARAMETER-EFFICIENT SOFT PROMPT TRANSFER
Xinglong Wu, C. L. Philip Chen, Shuzhen Li, Tony Zhang, South China University of Technology, China
SLP-P36.9: Exploring Soft Prompt Initialization Strategy for Few-shot Continual Text Classification
Zhehao Zhang, Dartmouth College, United States of America; Tong Yu, Handong Zhao, Adobe Research, United States of America; Kaige Xie, Georgia Institute of Technology, United States of America; Lina Yao, Data61, CSIRO & UNSW Sydney, Australia; Shuai Li, Shanghai Jiao Tong University, China
SLP-P36.10: Fovea Transformer: Efficient Long-Context Modeling with Structured Fine-to-Coarse Attention
Ziwei He, Jian Yuan, Le Zhou, Jingwen Leng, Bo Jiang, Shanghai Jiao Tong University, China
Contacts