Automatic Detection of Causal Relations for Question Answering
By Roxana Girju. 2003
417 citations recorded by the source corpus.
Causation relations are a pervasive feature of human language. Despite this, the automatic acquisition of causal information in text has proved to be a difficult task in NLP. This paper provides a method for the automatic detection and extraction of causal relations. We also present an inductive learning approach to the automatic discovery of lexical and semantic constraints necessary in the disambiguation of causal relations that are then used in question answering. We devised a classification of causal questions and tested the procedure on a QA system.
Subfields: Artificial Intelligence, Question Answering & Reading Comprehension, Causal Inference & Discovery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Iryna Gurevych
- Ting-Wei Liu
- Benjamin Van Durme
- Mohit Bansal
- Tat-seng Chua
- Xiao Ding
- Yejin Choi
- Zhongyang Li
In Question Answering & Reading Comprehension
- Angela Yao
- Tat-seng Chua
- Xiao Ding
- J. Edward Hu
- Xindi Shang
- Manfred Stede
- Andreas Peldszus
- Zhongyang Li
In Causal Inference & Discovery
- Zach Wood-Doughty
- Tat-seng Chua
- Xiao Ding
- Mark Dredze
- J. Edward Hu
- Ilya Shpitser
- Manfred Stede
- Andreas Peldszus
Citations in the corpus
- NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (2021, background): “Finally, we note that QA on causal and temporal events have long been studied in text comprehension [12, 34].”
- Guided Generation of Cause and Effect (2020, methodology): “Others have mined patterns via discourse patterns in the form of ‘A led to B’, ‘if A then B’, etc., e.g., [ Khoo et al. , 2000; Girju, 2003; Zhao et al. , 2017]).”
- Challenges of Using Text Classifiers for Causal Inference (2018, background): “There is a conceptually related line of work in the NLP community on inferring causal relationships expressed in text (Girju, 2003; Kaplan and Berry-Rogghe, 1991).”
- Automatic sense prediction for implicit discourse relations in text (2009, background): “For example, a question-answering application that needs to identify causal relations (i.e. as in Girju (2003)), must not only differentiate causal relations from comparison relations, but also from expansions, temporal relations, and possibly no relation at all.”
- From Argument Diagrams to Argumentation Mining in Texts: A Survey (2013, background): “To a large extent, this research has targeted intra-clausal patterns such as subject-verb-object triples involving causative (to lead to, to bring about, ...) and certain other verbs (see, e.g., Girju (2003)).”