# A Cross-Domain Evaluation of Approaches for Causal Knowledge Extraction

arXiv: https://arxiv.org/abs/2308.03891 · HTML: https://mlsanity.com/paper/2308.03891/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Span-based Joint Entity and Relation Extraction with Transformer Pre-training](https://mlsanity.com/paper/1909.07755/) (2019)
- [How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context](https://mlsanity.com/paper/2002.00652/) (2020)
- [Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings](https://mlsanity.com/paper/1904.07629/) (2019)
- [Domain Adaptative Causality Encoder](https://mlsanity.com/paper/2011.13549/) (2020)
- [Predicting Directionality in Causal Relations in Text](https://mlsanity.com/paper/2103.13606/) (2021)

## Built on by (most cited first, 1 of 1)

- [Diverse Explanations From Data-Driven and Domain-Driven Perspectives in the Physical Sciences](https://mlsanity.com/paper/2402.00347/) (2024)

## Abstract (arXiv)

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain have largely focused on binary classification of a text segment as causal or non-causal. In this regard, we perform a thorough analysis of three sequence tagging models for causal knowledge extraction and compare it with a span based approach to causality extraction. Our experiments show that embeddings from pre-trained language models (e.g. BERT) provide a significant performance boost on this task compared to previous state-of-the-art models with complex architectures. We observe that span based models perform better than simple sequence tagging models based on BERT across all 4 data sets from diverse domains with different types of cause-effect phrases.