2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDHLT-13.3
Paper Title IMPROVING EVENT DETECTION BY EXPLOITING LABEL HIERARCHY
Authors Xiangyu Xi, Meituan Group, China; Wei Ye, Tong Zhang, National Engineering Research Center for Software Engineering, Peking University, China; Quanxiu Wang, RICH AI, China; Shikun Zhang, National Engineering Research Center for Software Engineering, Peking University, China; Huixing Jiang, Wei Wu, Meituan Group, China
SessionHLT-13: Information Extraction
LocationGather.Town
Session Time:Thursday, 10 June, 14:00 - 14:45
Presentation Time:Thursday, 10 June, 14:00 - 14:45
Presentation Poster
Topic Human Language Technology: [HLT-MLMD] Machine Learning Methods for Language
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract Event types are hierarchical, yet most existing methods for event detection classify candidate triggers into fine-grained event types directly, without considering the rich semantic correlations in the hierarchy of event types. To fully utilize such information to improve the detection of fine-grained event types, we propose a three-layer label hierarchy and introduce the detection of two coarser-grained types as auxiliary classification tasks. In particular, we leverage the supplementary supervision information from label hierarchy by a novel Logits Mapping (LM) strategy, which generates logits (the intermediate representations fed into classifier) for coarser-grained types by heuristic mapping of logits for fine-grained types. In this way, training signals provided by auxiliary tasks can help the encoder produce more precise logits via back propagation, thus providing a simple (no extra parameter needed) yet effective way to improve the target task. Results of extensive experiments on the ACE 2005 show that LM can not only be easily integrated into the state-of-the-art methods and achieve significant improvement over them, but also can effectively alleviate the data sparseness problem.