Commonsense Causal Reasoning Using Millions of Personal Stories
By Andrew S. Gordon, Cosmin Adrian Bejan, Kenji Sagae. 2011
77 citations recorded by the source corpus.
The personal stories that people write in their Internet weblogs include a substantial amount of information about the causal relationships between everyday events. In this paper we describe our efforts to use millions of these stories for automated commonsense causal reasoning. Casting the commonsense causal reasoning problem as a Choice of Plausible Alternatives, we describe four experiments that compare various statistical and information retrieval approaches to exploit causal information in story corpora. The top performing system in these experiments uses a simple co-occurrence statistic between words in the causal antecedent and consequent, calculated as the Pointwise Mutual Information between words in a corpus of millions of personal stories.
Subfields: Artificial Intelligence
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
- Ting-Wei Liu
- Xiao Ding
- Zhongyang Li
- J. Edward Hu
- Jackie Chi Kit Cheung
- Adam Trischler
- Benjamin Van Durme
- Kaheer Suleman
Citations in the corpus
- Handling Multiword Expressions in Causality Estimation (2017, methodology): “Causal Strength is similar to pointwise mutual information (PMI) but more superior in modeling causality, combining two factors: the necessary factor and the sufficient factor.”
- When Choosing Plausible Alternatives, Clever Hans can be Clever (2019, methodology): “Prior to neural network approaches, the most dominant way of solving COPA was via Pointwise Mutual Information (PMI)-based statistics using a large background corpus between the content words in the premise and the alternatives (Gordon et al., 2011; Luo et al., 2016; Sasaki et al., 2017; Goodwin et ”
- A Knowledge Hunting Framework for Common Sense Reasoning (2018, methodology): “More recent work showed that applying the same PMI-based technique on a corpus of stories yields better results (Gordon et al., 2011).”
- Guided Generation of Cause and Effect (2020, background): “Many works have followed this strategy, e.g. [ Chambers and Jurafsky, 2008; Riaz and Girju, 2010; Gordon et al. , 2011; Do et al. , 2011; Luo et al. , 2016 ] .”