Modeling Event Salience in Narratives via Barthes’ Cardinal Functions

Events in a narrative differ in salience: some are more important to the story than others. Estimating event salience is useful for tasks such as story generation, and as a tool for text analysis in narratology and folkloristics. To compute event salience without any annotations, we adopt Barthes' definition of event salience and propose several unsupervised methods that require only a pre-trained language model. Evaluating the proposed methods on folktales with event salience annotation, we show that the proposed methods outperform baseline methods and find fine-tuning a language model on narrative texts is a key factor in improving the proposed methods.

[1]  Mirella Lapata,et al.  Modeling Local Coherence: An Entity-Based Approach , 2005, ACL.

[2]  Ruihong Huang,et al.  Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations , 2018, NAACL-HLT.

[3]  Nathanael Chambers,et al.  Unsupervised Learning of Narrative Schemas and their Participants , 2009, ACL.

[4]  James Allan,et al.  Joke retrieval: recognizing the same joke told differently , 2008, CIKM '08.

[5]  E. Rasmussen.  Evaluation in Information Retrieval , 2002 .

[6]  Sanja Fidler,et al.  Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[8]  Gilles Louppe,et al.  Independent consultant , 2013 .

[9]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[10]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[11]  Vishal Gupta,et al.  Recent automatic text summarization techniques: a survey , 2016, Artificial Intelligence Review.

[12]  William C. Mann,et al.  Rhetorical Structure Theory: Description and Construction of Text Structures , 1987 .

[13]  Dina Sherzer,et al.  A dictionary of narratology , 1989 .

[14]  Raymond J. Mooney,et al.  Learning Statistical Scripts with LSTM Recurrent Neural Networks , 2016, AAAI.

[15]  André Freitas,et al.  A Survey on Open Information Extraction , 2018, COLING.

[16]  Hinrich Schütze,et al.  Introduction to Information Retrieval: Evaluation in information retrieval , 2008 .

[17]  R. Barthes.  Introduction à l'analyse structurale des récits , 1966 .

[18]  Daniel Jurafsky,et al.  Neural Net Models of Open-domain Discourse Coherence , 2016, EMNLP.

[19]  Frank Keller,et al.  Movie Plot Analysis via Turning Point Identification , 2019, EMNLP.

[20]  Mark T. Maybury,et al.  Automatic Summarization , 2002, Computational Linguistics.

[21]  Nathanael Chambers,et al.  A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories , 2016, NAACL.

[22]  Mark O. Riedl,et al.  Event Representations for Automated Story Generation with Deep Neural Nets , 2017, AAAI.

[23]  Joel R. Tetreault,et al.  Discourse Coherence in the Wild: A Dataset, Evaluation and Methods , 2018, SIGDIAL Conference.

[24]  Mark A. Finlayson.  ProppLearner: Deeply annotating a corpus of Russian folktales to enable the machine learning of a Russian formalist theory , 2017, Digit. Scholarsh. Humanit..

[25]  Vladimir Propp,et al.  Morphology of the folktale , 1959 .

[26]  R'emi Louf,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[27]  Frank Keller,et al.  Suspense in Short Stories is Predicted By Uncertainty Reduction over Neural Story Representation , 2020, ACL.

[28]  Christopher D. Manning,et al.  Do Massively Pretrained Language Models Make Better Storytellers? , 2019, CoNLL.

[29]  Maki Watanabe,et al.  Discourse Tagging Reference Manual , 2001 .

[30]  Teruko Mitamura,et al.  Automatic Event Salience Identification , 2018, EMNLP.

[31]  Kentaro Inui,et al.  Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis , 2019, EMNLP/IJCNLP.

[32]  Kathleen McKeown,et al.  Modeling Reportable Events as Turning Points in Narrative , 2015, EMNLP.

[33]  H. Abbott.  The Cambridge Introduction to Narrative , 2020 .

[34]  Hitoshi Isahara,et al.  Evaluation of Features for Sentence Extraction on Different Types of Corpora , 2003, ACL 2003.

[35]  Anna Kazantseva,et al.  Summarizing Short Stories , 2010, CL.

[36]  Garrison W. Cottrell,et al.  Improving Neural Story Generation by Targeted Common Sense Grounding , 2019, EMNLP.

[37]  R. Barthes,et al.  An Introduction to the Structural Analysis of Narrative , 1975 .

[38]  Minlie Huang,et al.  A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation , 2020, TACL.