Summarizing Information by Means of Causal Sentences Through Causal Questions

Puente, Cristina; Sobrino, Alejandro; Garrido, E.; Olivas, José Á.

doi:10.1007/978-3-319-19719-7_31

Cited by 2 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There were a number of papers that constructed causal networks (Ishii, Ma, and Yoshikawa 2010b;Ishii et al 2010a;Ackerman 2012;Puente, Garrido, and Olivas 2013a;Puente, Olivas, and Prado 2014;Luo et al 2016;Zhao et al 2017;Kang et al 2017) from causal relations extracted from documents. These networks were constructed with the purpose of supporting other tasks such as news understanding (Ishii et al 2010a), text summarisation (Puente et al 2014), questionanswering (Puente et al 2013a) and commonsense reasoning (Luo et al 2016).…”

Section: Causal Information Modellingmentioning

confidence: 99%

“…The event keywords are given context by the topic keywords which complement the causal description provided by the edges. The text summarisation approach proposed by Puente et al (2014) constructed a causal graph from the extraction of causal relations from the target document. A summary generated by the causal network is extracted by identifying the most relevant information using standard extractive summarisation techniques such as term-frequency inverse document frequency (TF-IDF).…”

Section: Causal Information Modellingmentioning

confidence: 99%

“…The approach proposed by Puente et al (2013a) used a causal network as background information to support a question-answering system. The approach was almost identical to their technique for extractive summarisation (Puente et al 2014). Commonsense causal reasoning 'is the process of capturing and understanding the causal dependencies amongst events and actions' (Luo et al 2016).…”

Section: Causal Information Modellingmentioning

confidence: 99%

“…The literature review found four types of summarisation that have used textual causal relations. The strategies covered structured summarisation Tanaka 2016a, 2016b), abstractive summarisation (Puente et al 2014;Puente et al 2013b;Puente et al 2016) and extractive summarisation (Puente et al 2017).…”

Section: Text Summarisationmentioning

confidence: 99%

See 3 more Smart Citations

A survey of the extraction and applications of causal relations

Drury

Oliveira

Lopes³

2022

Nat. Lang. Eng.

View full text Add to dashboard Cite

Causationin written natural language can express a strong relationship between events and facts. Causation in the written form can be referred to as a causal relation where a cause event entails the occurrence of an effect event. A cause and effect relationship is stronger than a correlation between events, and therefore aggregated causal relations extracted from large corpora can be used in numerous applications such as question-answering and summarisation to produce superior results than traditional approaches. Techniques like logical consequence allow causal relations to be used in niche practical applications such as event prediction which is useful for diverse domains such as security and finance. Until recently, the use of causal relations was a relatively unpopular technique because the causal relation extraction techniques were problematic, and the relations returned were incomplete, error prone or simplistic. The recent adoption of language models and improved relation extractors for natural language such as Transformer-XL (Dai et al. (2019). Transformer-xl: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860) has seen a surge of research interest in the possibilities of using causal relations in practical applications. Until now, there has not been an extensive survey of the practical applications of causal relations; therefore, this survey is intended precisely to demonstrate the potential of causal relations. It is a comprehensive survey of the work on the extraction of causal relations and their applications, while also discussing the nature of causation and its representation in text.

show abstract

Section: Causal Information Modellingmentioning

confidence: 99%

Section: Causal Information Modellingmentioning

confidence: 99%

Section: Causal Information Modellingmentioning

confidence: 99%

Section: Text Summarisationmentioning

confidence: 99%

See 2 more Smart Citations

A survey of the extraction and applications of causal relations

Drury

Oliveira

Lopes³

2022

Nat. Lang. Eng.

View full text Add to dashboard Cite

show abstract

“…We will also propose a system that uses the model to tackle fake news [9]. Summarizing the causal information [18] [21] [20] with the learned uncertainty is also a pending task. Another interesting line of work is proposing an evaluation measure of the graph and then optimizing the priors and types of the distributions to detect which are the best prior distributions their hyperparameters.…”

Section: Conclusion and Further Workmentioning

confidence: 99%

Uncertainty Weighted Causal Graphs

Garrido-Merchán¹,

Puente²,

Sobrino³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Causality has traditionally been a scientific way to generate knowledge by relating causes to effects. From an imaginery point of view, causal graphs are a helpful tool for representing and infering new causal information. In previous works, we have generated automatically causal graphs associated to a given concept by analyzing sets of documents and extracting and representing the found causal information in that visual way. The retrieved information shows that causality is frequently imperfect rather than exact, feature gathered by the graph. In this work we will attempt to go a step further modelling the uncertainty in the graph through probabilistic improving the management of the imprecision in the quoted graph.

show abstract

Summarizing Information by Means of Causal Sentences Through Causal Questions

Cited by 2 publications

References 12 publications

A survey of the extraction and applications of causal relations

A survey of the extraction and applications of causal relations

Uncertainty Weighted Causal Graphs

Contact Info

Product

Resources

About