Discovering Concept-Level Event Associations from a Text Stream

Ge, Tao; Cui, Lei; Ji, Heng; Chang, Baobao; Sui, Zhifang

doi:10.1007/978-3-319-50496-4_34

“…In the latter case, e 0 acts as a confounder between e 1 and e 2 . Ge et al (2016) acknowledges that the associations picked up by correlational measures may often be spurious. Their solution relies on using trends of words in a temporal stream of newswire data, and hence is fairly domain specific.…”

Section: The Significance Of Causal Relevancementioning

confidence: 99%

“…Consider the example of Ge et al (2016): hurricane events are prototypically connected with events of donations coming in. Likewise, hurricane events are connected to evacuation events.…”

Section: Introductionmentioning

confidence: 99%

Causal Inference of Script Knowledge

Weber

¹

,

Rudinger²,

Durme

³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

When does a sequence of events define an everyday scenario and how can this knowledge be induced from text? Prior works in inducing such scripts have relied on, in one form or another, measures of correlation between instances of events in a corpus. We argue from both a conceptual and practical sense that a purely correlation-based approach is insufficient, and instead propose an approach to script induction based on the causal effect between events, formally defined via interventions. Through both human and automatic evaluations, we show that the output of our method based on causal effects better matches the intuition of what a script represents.

show abstract

“…In the latter case, e 0 acts essentially as a confounder between e 1 and e 2 . Ge et al (2016) acknowledges that the associations picked up by correlational measures may often be spurious (seen by the example in the intro). Their solution relies on using trends of words in a temporal stream of newswire data, and hence is fairly domain specific.…”

Section: The Significance Of Causal Relevancementioning

confidence: 99%

“…An example given in Ge et al (2016) illustrates this point: a hurricane event may be prototypically connected with the event of donations coming in. Likewise, the hurricane event may also be connected to an evacuation.…”

Section: Introductionmentioning

confidence: 97%

Causal Inference of Script Knowledge

Weber¹,

Rudinger²,

Durme³

2020

Preprint

0

View full text Add to dashboard Cite

When does a sequence of events define an everyday scenario and how can this knowledge be induced from text? Prior works in inducing such scripts have relied on, in one form or another, measures of correlation between instances of events in a corpus. We argue from both a conceptual and practical sense that a purely correlation-based approach is insufficient, and instead propose an approach to script induction based on the causal effect between events, formally defined via interventions. Through both human and automatic evaluations, we show that the output of our method based on causal effects better matches the intuition of what a script represents.2 What is 'high enough' depends on the method of course, for example, in PMI p(e2|e1) needs to be higher than p(e2)

show abstract