Please use this identifier to cite or link to this item:Volltext verfügbar? / Dokumentlieferung
|Title:||A Systematic Study of Neural Discourse Models for Implicit Discourse Relation|
Camilleri, John J.
Coll Ardanuy, Mariona
|Title:||European Chapter of the Association for Computational Linguistics - proceedings of the Student Research Workshop|
|Year of Publication:||2017|
|Place of publication:||Stroudsburg, PA|
|Title of the Conference:||EACL 2017|
|Place of the conference:||Valencia, Spain|
|Publikation type:||Conference Paper|
|Abstract:||Inferring implicit discourse relations in natural language text is the most difficult subtask in discourse parsing. Many neural network models have been proposed to tackle this problem. However, the comparison for this task is not unified, so we could hardly draw clear conclusions about the effectiveness of various architectures. Here, we propose neural network models that are based on feedforward and long-short term memory architecture and systematically study the effects of varying structures. To our surprise, the best-configured feedforward architecture outperforms LSTM-based model in most cases despite thorough tuning. Further, we compare our best feedforward system with competitive convolutional and recurrent networks and find that feedforward can actually be more effective. For the first time for this task, we compile and publish outputs from previous neural and non-neural systems to establish the standard for further comparison.|
|DOI of the first publication:||10.18653/v1/E17-1027|
|URL of the first publication:||https://www.aclweb.org/anthology/E17-1027/|
|Link to this record:||hdl:20.500.11880/29701|
|Date of registration:||22-Sep-2020|
|Faculty:||MI - Fakultät für Mathematik und Informatik|
|Department:||MI - Informatik|
|Professorship:||MI - Prof. Dr. Vera Demberg|
|Collections:||UniBib – Die Universitätsbibliographie|
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.