Event-Related Features in Feedforward Neural Networks Contribute to Identifying Implicit Causal Relations in Discourse
MetadataShow full item record
Ponti, E., & Korhonen, A. (2017). Event-Related Features in Feedforward Neural Networks Contribute to Identifying Implicit Causal Relations in Discourse. EACL 2017. https://doi.org/10.17863/CAM.9725
Causal relations play a key role in information extraction and reasoning. Most of the times, their expression is ambiguous or implicit, i.e. without signals in the text. This makes their identification challenging. We aim to improve their identification by implementing a Feedforward Neural Network with a novel set of features for this task. In particular, these are based on the position of event mentions and the semantics of events and participants. The resulting classifier outperforms strong baselines on two datasets (the Penn Discourse Treebank and the CSTNews corpus) annotated with different schemes and containing examples in two languages, English and Portuguese. This result demonstrates the importance of events for identifying discourse relations.
Discourse Relations, NLP, Multi-Layer Perceptron, Event Semantics
ECH2020 EUROPEAN RESEARCH COUNCIL (ERC) (648909)
This record's DOI: https://doi.org/10.17863/CAM.9725
This record's URL: https://www.repository.cam.ac.uk/handle/1810/269546