Skip to content

Models

Model approaches for causality extraction, ranging from interpretable rule-based baselines to fine-tuned neural classifiers.

Task codes: D = Detection · E = Extraction · I = Identification

Model Type Tasks Reference Links
Biaffine Span-Grid Extraction Neural read-out layer (causalatee.nn.BiaffineSpanHead) E (Yu et al. 2020)1 📄
Causal Connective Lexicon Rule-based lexicon lookup (causalatee.nlp.LexiconDetector) D (Girju 2003)2 📄
k-CNN Knowledge- + data-channel CNN for relation classification I (Li and Mao 2019)3 📄
SCITE BiLSTM + char-CNN + Flair/BERT + self-attention + CRF E (Li et al. 2021)4 📄
SDP Causality Extraction Dependency-based baseline I (Girju 2003)2 📄
Sentence Embeddings Fine-tuned pretrained transformer encoder (dense sentence/token embeddings) DEI — —

Neural fine-tuning approaches (RoBERTa etc.) are covered in the Examples section.

  1. Yu, Juntao, Bernd Bohnet, and Massimo Poesio. 2020. “Named Entity Recognition as Dependency Parsing.” In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, edited by Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault. Association for Computational Linguistics. https://doi.org/10.18653/V1/2020.ACL-MAIN.577. ↩

  2. Girju, Roxana. 2003. “Automatic Detection of Causal Relations for Question Answering.” Proceedings of the ACL 2003 Workshop on Multilingual Summarization and Question Answering (Sapporo, Japan), 76–83. https://doi.org/10.3115/1119312.1119322. ↩↩

  3. Li, Pengfei, and Kezhi Mao. 2019. “Knowledge-Oriented Convolutional Neural Network for Causal Relation Extraction from Natural Language Texts.” Expert Syst. Appl. 115: 512–23. https://doi.org/10.1016/J.ESWA.2018.08.009. ↩

  4. Li, Zhaoning, Qi Li, Xiaotian Zou, and Jiangtao Ren. 2021. “Causality Extraction Based on Self-Attentive BiLSTM-CRF with Transferred Embeddings.” Neurocomputing 423: 207–19. https://doi.org/10.1016/J.NEUCOM.2020.08.078. ↩