Inferring Interpersonal Relations in Narrative Summaries

Characterizing relationships between people is fundamental for the understanding of narratives. In this work, we address the problem of inferring the polarity of relationships between people in narrative summaries. We formulate the problem as a joint structured prediction for each narrative, and present a model that combines evidence from linguistic and semantic features, as well as features based on the structure of the social community in the text. We also provide a clustering-based approach that can exploit regularities in narrative types. e.g., learn an affinity for love-triangles in romantic stories. On a dataset of movie summaries from Wikipedia, our structured models provide more than a 30% error-reduction over a competitive baseline that considers pairs of characters in isolation.

[1]  Owen Rambow,et al.  Automatic Extraction of Social Networks from Literary Text: A Case Study on Alice in Wonderland , 2013, IJCNLP.

[2]  Rafael Alonso,et al.  Extracting Social Power Relationships from Natural Language , 2011, ACL.

[3]  Brendan T. O'Connor,et al.  Learning Latent Personas of Film Characters , 2013, ACL.

[4]  Yang Guo,et al.  Structured Perceptron with Inexact Search , 2012, NAACL.

[5]  Nathanael Chambers,et al.  Event Schema Induction with a Probabilistic Entity-Driven Model , 2013, EMNLP.

[6]  Jure Leskovec,et al.  Signed networks in social media , 2010, CHI.

[7]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[8]  Mark A. Finlayson.  Learning narrative structure from annotated folktales , 2012 .

[9]  Nathanael Chambers,et al.  Unsupervised Learning of Narrative Event Chains , 2008, ACL.

[10]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[11]  F. Harary,et al.  STRUCTURAL BALANCE: A GENERALIZATION OF HEIDER'S THEORY1 , 1977 .

[12]  Dragomir R. Radev,et al.  Extracting Signed Social Networks from Text , 2012, TextGraphs@ACL.

[13]  Bing Liu,et al.  Opinion observer: analyzing and comparing opinions on the Web , 2005, WWW '05.

[14]  Jichen Zhu,et al.  Toward Automatic Role Identification in Unannotated Folk Tales , 2014, AIIDE.

[15]  Jacob Eisenstein,et al.  "You're Mr. Lebowski, I'm the Dude": Inducing Address Term Formality in Signed Social Networks , 2015, HLT-NAACL.

[16]  Ramesh Nallapati,et al.  Joint question clustering and relevance prediction for open domain non-factoid question answering , 2014, WWW.

[17]  David Bamman,et al.  A Bayesian Mixed Effects Model of Literary Character , 2014, ACL.

[18]  Noah A. Smith,et al.  Frame-Semantic Parsing , 2014, CL.

[19]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[20]  Apoorv Agarwal,et al.  Parsing Screenplays for Extracting Social Networks from Movies , 2014, CLfL@EACL.

[21]  Massimiliano Pontil,et al.  Regularized multi--task learning , 2004, KDD.

[22]  F. Heider.  Attitudes and cognitive organization. , 1946, The Journal of psychology.

[23]  Chris Dyer,et al.  Modeling Dynamic Relationships Between Characters in Literary Novels , 2015, ArXiv.

[24]  Kathleen McKeown,et al.  Extracting Social Networks from Literary Fiction , 2010, ACL.

[25]  Sampo Pyysalo,et al.  brat: a Web-based Tool for NLP-Assisted Text Annotation , 2012, EACL.

[26]  Roger C. Schank,et al.  Scripts, plans, goals and understanding: an inquiry into human knowledge structures , 1978 .

[27]  Yejin Choi,et al.  Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning , 2013, ACL.