Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution

Wenqiang Lei, Yuanxin Xiang, Yuwei Wang, Qian Zhong, Meichun Liu, Min-Yen Kan

AAAI 2018 pp. 4848-4855

doi:10.1609/AAAI.V32I1.11933 /aaai/2018/lei2018aaai-linguistic/

Abstract

Modern solutions for implicit discourse relation recognition largely build universal models to classify all of the different types of discourse relations. In contrast to such learning models, we build our model from first principles, analyzing the linguistic properties of the individual top-level Penn Discourse Treebank (PDTB) styled implicit discourse relations: Comparison, Contingency and Expansion. We find semantic characteristics of each relation type and two cohesion devices---topic continuity and attribution---work together to contribute such linguistic properties. We encode those properties as complex features and feed them into a NaiveBayes classifier, bettering baselines(including deep neural network ones) to achieve a new state-of-the-art performance level. Over a strong, feature-based baseline, our system outperforms one-versus-other binary classification by 4.83% for Comparison relation, 3.94% for Contingency and 2.22% for four-way classification.

PDF AAAI Semantic Scholar

Cite

Text

Lei et al. "Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11933

Markdown

[Lei et al. "Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/lei2018aaai-linguistic/) doi:10.1609/AAAI.V32I1.11933

BibTeX

@inproceedings{lei2018aaai-linguistic,
  title     = {{Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution}},
  author    = {Lei, Wenqiang and Xiang, Yuanxin and Wang, Yuwei and Zhong, Qian and Liu, Meichun and Kan, Min-Yen},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {4848-4855},
  doi       = {10.1609/AAAI.V32I1.11933},
  url       = {https://mlanthology.org/aaai/2018/lei2018aaai-linguistic/}
}