We consider the problem of collectively detecting multiple events,particularly in cross-sentence settings . We reformulate it as a Seq2Seq task and propose a Multi-Layer Bidirectional Network (MLBiNet) to capture the document-level association of events and semantic information simultaneously . An abidirectional decoder is devised to model event inter-dependency withina sentence when decoding the event tag vector sequence. Secondly, aninformation aggregation module is employed to aggregate sentence-level semanticand event tag information. Finally, we stack multiple biddirectional decodersand feed . information, forming a multi-layer bidirectionaltagging architecture to iteratively propagate information across sentences .

Author(s) : Dongfang Lou, Zhilin Liao, Shumin Deng, Ningyu Zhang, Huajun Chen

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : information - event - sentence - mlbinet - tag -

Leave a Reply

Your email address will not be published. Required fields are marked *