IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
SPE-74: Representations and Relationships in Language
Thu, 12 May, 22:00 - 22:45 China Time (UTC +8)
Thu, 12 May, 14:00 - 14:45 UTC
Location: Gather Area E
Session Co-Chairs: Sibel Oyman, Apple and Malu Zhang, University of Electronic Science and Technology of China
Track: Speech and Language Processing

SPE-74.1: INTEGRATING DEPENDENCY TREE INTO SELF-ATTENTION FOR SENTENCE REPRESENTATION
Junhua Ma, Yuxuan Liu, Shangbo Zhou, Chongqing University, China; Jiajun Li, Xue Li, The University of Queensland, Australia

SPE-74.2: MetricBERT: Text Representation Learning via Self-Supervised Triplet Training
Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Yoni Weill, Noam Koenigstein, microsoft, Israel

SPE-74.4: End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline
Tuan Lai, University of Illinois at Urbana-Champaign, United States of America; Trung Bui, Adobe, United States of America; Doo-Soon Kim, Roku, Inc., United States of America

SPE-74.5: LOCAL CONTEXT INTERACTION-AWARE GLYPH-VECTORS FOR CHINESE SEQUENCE TAGGING
JunYu Lu, PingJian Zhang, South China University of Technology, China