Learning to Predict from Textual Data

Radinsky, Kira; Davidovich, Sagie; Markovitch, Shaul

doi:10.1613/jair.3865

Cited by 28 publications

(27 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mining and creation of future prediction rules. The work in [32], suggests exploiting causal reasoning for future prediction. However, temporal reasoning does not equal causal reasoning.…”

Section: Memory Network and Other Related Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging knowledge bases for future prediction with memory comparison networks

Andrade

Bai²,

Rajendran

et al. 2018

AIC

View full text Add to dashboard Cite

Making predictions about what might happen in the future is important for reacting adequately in many situations. For example, observing that "Man kidnaps girl" may have the consequence that "Man kills girl". While this is part of common sense reasoning for humans, it is not obvious how machines can acquire and generalize over such knowledge. In this article, we propose a new type of memory network that can predict the next future event also for observations that are not in the knowledge base. We evaluate our proposed method on two knowledge bases: Reuters KB (events from news articles) and Regneri KB (events from scripts). For both knowledge bases, our proposed method shows similar or better prediction accuracy on unseen events (or scripts) than recently proposed deep neural networks and rankSVM. We also demonstrate that the attention mechanism of our proposed method can be helpful for error analysis and manual expansion of the knowledge base.

show abstract

“…Mining and creation of future prediction rules. The work in [32], suggests exploiting causal reasoning for future prediction. However, temporal reasoning does not equal causal reasoning.…”

Section: Memory Network and Other Related Neural Networkmentioning

confidence: 99%

“…However, the causal reason for "minister leaves hall" is, for example, that "the conference ended". Another difference of our approach to the method in [32] is that we exploit word embeddings for generalization rather than relying on the completeness of manually created ontologies.…”

Section: Memory Network and Other Related Neural Networkmentioning

confidence: 99%

Leveraging knowledge bases for future prediction with memory comparison networks

Andrade

Bai²,

Rajendran

et al. 2018

AIC

View full text Add to dashboard Cite

show abstract

“…Even though there are related works on event identification in emotion cause detection, there is no formal definition of events In area of artificial intelligence (AI), researchers, such as Radinsky (Radinsky et al, 2012), gave a formal definition of an event as "action, actor, object, instrument, location and time". In our work, we need to give clear definition of event first.…”

Section: Event Tree Constructionmentioning

confidence: 99%

Event-Driven Emotion Cause Extraction with Corpus Construction

Gui¹,

Wu²,

Xu³

et al. 2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

137

View full text Add to dashboard Cite

In this paper, we present our work in emotion cause extraction. Since there is no open dataset available, the lack of annotated resources has limited the research in this area. Thus, we first present a dataset we built using SINA city news. The annotation is based on the scheme of the W3C Emotion Markup Language. Second, we propose a 7-tuple definition to describe emotion cause events. Based on this general definition, we propose a new event-driven emotion cause extraction method using multi-kernel SVMs where a syntactical tree based approach is used to represent events in text. A convolution kernel based multikernel SVM are used to extract emotion causes. Because traditional convolution kernels do not use lexical information at the terminal nodes of syntactic trees, we modify the kernel function with a synonym based improvement. Even with very limited training data, we can still extract sufficient features for the task. Evaluations show that our approach achieves 11.6% higher F-measure compared to referenced methods. The contributions of our work include resource construction, concept definition and algorithm development.

show abstract

“…A recent follow-up work [34] extended the analysis to Web queries. Another approach modeled causality of events by using background data from the Linked Open Data cloud [32]. These works were the first to address the prediction of events at large scale.…”

Section: State Of the Artmentioning

confidence: 99%

Semantic culturomics

Suchanek

Preda

2014

Proc. VLDB Endow.

View full text Add to dashboard Cite

Newspapers are testimonials of history. The same is increasingly true of social media such as online forums, online communities, and blogs. By looking at the sequence of articles over time, one can discover the birth and the development of trends that marked society and history-a field known as "Culturomics". But Culturomics has so far been limited to statistics on keywords. In this vision paper, we argue that the advent of large knowledge bases (such as YAGO [37], NELL [5], DBpedia [3], and Freebase) will revolutionize the field. If their knowledge is combined with the news articles, it can breathe life into what is otherwise just a sequence of words for a machine. This will allow discovering trends in history and culture, explaining them through explicit logical rules, and making predictions about the events of the future. We predict that this could open up a new field of research, "Semantic Culturomics", in which no longer human text helps machines build up knowledge bases, but knowledge bases help humans understand their society.

show abstract

Learning to Predict from Textual Data

Cited by 28 publications

References 89 publications

Leveraging knowledge bases for future prediction with memory comparison networks

Leveraging knowledge bases for future prediction with memory comparison networks

Event-Driven Emotion Cause Extraction with Corpus Construction

Semantic culturomics

Contact Info

Product

Resources

About