Constructing Narrative Event Evolutionary Graph for Script Event Prediction

By Zhongyang Li, Xiao Ding, Ting-Wei Liu. 2018

218 citations recorded by the source corpus.

Script event prediction requires a model to predict the subsequent event given an existing event context. Previous models based on event pairs or event chains cannot make full use of dense event connections, which may limit their capability of event prediction. To remedy this, we propose constructing an event graph to better utilize the event network information for script event prediction. In particular, we first extract narrative event chains from large quantities of news corpus, and then construct a narrative event evolutionary graph (NEEG) based on the extracted chains. NEEG can be seen as a knowledge base that describes event evolutionary principles and patterns. To solve the inference problem on NEEG, we present a scaled graph neural network (SGNN) to model event interactions and learn better event representations. Instead of computing the representations on the whole graph, SGNN processes only the concerned nodes each time, which makes our model feasible to large-scale graphs. By comparing the similarity between input context event representations and candidate event representations, we can choose the most reasonable subsequent event. Experimental results on widely used New York Times corpus demonstrate that our model significantly outperforms state-of-the-art baseline methods, by using standard multiple choice narrative cloze evaluation.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Natural Language Processing

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

In Statistical and Nonlinear Physics

In Natural Language Processing

Citations in the corpus

Story Ending Prediction by Transferable BERT (2019, methodology): “SeqMANN [Li et al. , 2018a] integrated external knowledge into a multi-attention network.”
“Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding (2019, background): “what happens next after certain events) (GranrothWilding and Clark, 2016; Li et al., 2018).”
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning (2020, background): “…series of events (Schank and Abelson, 1977; Chambers and Jurafsky, 2008; Pichotta and Mooney, 2014), temporal common-sense (Granroth-Wilding and Clark, 2016; Li et al., 2018), and modeling pre-and post-conditions of events (Roemmele et al., 2011; Sap et al., 2019; Bosselut et al., 2019).”
Guided Generation of Cause and Effect (2020, methodology): “We designed an intermediate task for BERT using CausalBank B, employing margin loss [Li et al., 2019a; Li et al., 2018a] in the objective function: L(Θ) = ∑ (c,e)∈B (max(0,m− f (c, e) + f (c′, e′))) + λ2 | |Θ| |2, where f (c, e) is the score of true CE pair given by BERT model, f (c′, e′) is the sco”
ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data (2020, background): “Another approach is script-learning, in which a model is provided with a chain of events and a subsequent event and is asked to predict the relation between the chain and the “future” event (Hu et al., 2017; Li et al., 2018; Lv et al., 2019).”
A Survey on Text Classification: From Traditional to Deep Learning (2020, unknown): “SGNN [213] is proposed to model event interactions and learn better event representations by constructing an event graph to utilize the event network information better.”
Temporal Common Sense Acquisition with Minimal Supervision (2020, background): “, what happens next after certain events) (Granroth-Wilding and Clark, 2016; Li et al., 2018; Peng et al., 2019).”
A Survey on Text Classification: From Shallow to Deep Learning (2020, unknown): “SGNN [76] is proposed to model event interactions and learn better event representations by constructing an event graph to utilize the event network information better.”
Session-based Recommendation with Graph Neural Networks (2018, methodology): “Recently, GNN is broadly applied for the different tasks, e.g., script event prediction (Li, Ding, and Liu 2018), situation recognition (Li et al. 2017b), and image classiﬁcation (Marino, Salakhutdinov, and Gupta 2017).”