Integrating Order Information and Event Relation for Script Event Prediction

Wang, Zhongqing; Zhang, Yue; Chang, Ching-Yun

doi:10.18653/v1/d17-1006

Cited by 66 publications

(84 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore our proposed method should unify both short-term sequential dependency (at both individual-level and union-level) and long-term sequential dependency. Inspired by [18]…”

Section: Multi-relational Dependency Modeling For Short-term Patternmentioning

confidence: 99%

Joint Relational Dependency Learning for Sequential Recommendation

Wang

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Sequential recommendation leverages the temporal information of users' transactions as transition dependencies for better inferring user preference, which has become increasingly popular in academic research and practical applications. Short-term transition dependencies contain the information of partial item orders, while long-term transition dependencies infer long-range user preference, the two dependencies are mutually restrictive and complementary. Although some work investigates unifying both long-term and short-term dependencies for better performance, they still neglect the fact that short-term interactions are multi-folds, which are either individual-level interactions or unionlevel interactions. Existing sequential recommendations mainly focus on user's individual (i.e., individual-level) interactions but ignore the important collective influence at union-level. Since union-level interactions can reflect that human decisions are made based on multiple items he/she has already interacted, ignoring such interactions can result in the disability of capturing the collective influence between items. To alleviate this issue, we proposed a Joint Relational Dependency learning (JRD-L) for sequential recommendation that exploits both long-term and short-term preferences at individual-level and union-level. Specifically, JRD-L combines long-term user preferences with short-term interests by measuring shortterm pair relations at individual-level and union-level. Moreover, JRD-L can alleviate the sparsity problem of union-level interactions by adding more descriptive details to each item, which is carried by individual-level relations. Extensive numerical experiments demonstrate JRD-L outperforms state-of-the-art baselines for the sequential recommendation.

show abstract

“…Therefore our proposed method should unify both short-term sequential dependency (at both individual-level and union-level) and long-term sequential dependency. Inspired by [18]…”

Section: Multi-relational Dependency Modeling For Short-term Patternmentioning

confidence: 99%

Joint Relational Dependency Learning for Sequential Recommendation

Wang

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…Recently a growing number of studies focus on event-centered commonsense reasoning, which mainly concentrates on two areas, script event prediction and story ending generation/choosing. Script event prediction concerns with the temporal relationships between script events (Granroth-Wilding and Clark, 2016), which requires models to choose a correct subsequent triple-organized event among the candidates (Wang et al, 2017). Prior work mainly focused on modeling event pairs (Granroth-Wilding and Clark, 2016), event chains (Wang et al, 2017) and event graph (Li et al, 2018) to predict the subse-quent event.…”

Section: Event-centered Commonsense Reasoningmentioning

confidence: 99%

“…Script event prediction concerns with the temporal relationships between script events (Granroth-Wilding and Clark, 2016), which requires models to choose a correct subsequent triple-organized event among the candidates (Wang et al, 2017). Prior work mainly focused on modeling event pairs (Granroth-Wilding and Clark, 2016), event chains (Wang et al, 2017) and event graph (Li et al, 2018) to predict the subse-quent event. Story ending generation focuses on generating plausible story endings , which requires models to understand the story context, and keep generated endings logically consistent with it (Peng et al, 2017;Guan et al, 2019).…”

Section: Event-centered Commonsense Reasoningmentioning

confidence: 99%

Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder

Du¹,

Ding²,

Liu³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Understanding event and event-centered commonsense reasoning are crucial for natural language processing (NLP). Given an observed event, it is trivial for human to infer its intents and effects, while this type of If-Then reasoning still remains challenging for NLP systems. To facilitate this, a If-Then commonsense reasoning dataset Atomic is proposed, together with an RNN-based Seq2Seq model to conduct such reasoning. However, two fundamental problems still need to be addressed: first, the intents of an event may be multiple, while the generations of RNN-based Seq2Seq models are always semantically close; second, external knowledge of the event background may be necessary for understanding events and conducting the If-Then reasoning. To address these issues, we propose a novel context-aware variational autoencoder effectively learning event background information to guide the If-Then reasoning. Experimental results show that our approach improves the accuracy and diversity of inferences compared with state-of-the-art baseline methods.

show abstract

“…Multiple Choice version of the Narrative Cloze task (MCNC) proposed by Granroth-Wilding and Clark (2016); Wang et al (2017), aims to eval-uate understanding of a script by predicting the next event given several context events. Presenting a chain of contextual events e 1 , e 2 , ..., e n−1 , the task is to select the next event from five event candidates, one of which is correct and the others are randomly sampled elsewhere in the corpus.…”

Section: Narrative Clozementioning

confidence: 99%

“…Pichotta and Mooney (2016) introduced a LSTM-based language model for event prediction. Wang et al (2017) used dynamic memory as attention in LSTM for prediction. It is encouraging that by using event knowledge extracted from automatically identified narratives, we achieved the best event prediction performance, which is 2.2% higher than the best neural network model.…”

Section: Narrative Clozementioning

confidence: 99%

Temporal Event Knowledge Acquisition via Identifying Narratives

Yao¹,

Huang²

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Inspired by the double temporality characteristic of narrative texts, we propose a novel approach for acquiring rich temporal "before/after" event knowledge across sentences in narrative stories. The double temporality states that a narrative story often describes a sequence of events following the chronological order and therefore, the temporal order of events matches with their textual order. We explored narratology principles and built a weakly supervised approach that identifies 287k narrative paragraphs from three large text corpora. We then extracted rich temporal event knowledge from these narrative paragraphs. Such event knowledge is shown useful to improve temporal relation classification and outperform several recent neural network models on the narrative cloze task.

show abstract

Integrating Order Information and Event Relation for Script Event Prediction

Cited by 66 publications

References 18 publications

Joint Relational Dependency Learning for Sequential Recommendation

Joint Relational Dependency Learning for Sequential Recommendation

Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder

Temporal Event Knowledge Acquisition via Identifying Narratives

Contact Info

Product

Resources

About