Unsupervised Induction of Contingent Event Pairs from Film Scenes

Human engagement in narrative is partially driven by reasoning about discourse relations between narrative events, and the expectations about what is likely to happen next that results from such reasoning. Researchers in NLP have tackled modeling such expectations from a range of perspectives, including treating it as the inference of the CONTINGENT discourse relation, or as a type of common-sense causal reasoning. Our approach is to model likelihood between events by drawing on several of these lines of previous work. We implement and evaluate different unsupervised methods for learning event pairs that are likely to be CONTINGENT on one another. We refine event pairs that we learn from a corpus of film scene descriptions utilizing web search counts, and evaluate our results by collecting human judgments of contingency. Our results indicate that the use of web search counts increases the average accuracy of our best method to 85.64% over a baseline of 50%, as compared to an average accuracy of 75.15% without web search.

[1]  Pietro Perona,et al.  The Multidimensional Wisdom of Crowds , 2010, NIPS.

[2]  Jian Peng,et al.  Variational Inference for Crowdsourcing , 2012, NIPS.

[3]  Marilyn A. Walker,et al.  An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style , 2012, LREC.

[4]  David S. Miall Experiencing narrative worlds: On the psychological activities of reading , 2000 .

[5]  Brendan T. O'Connor,et al.  Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks , 2008, EMNLP.

[6]  W. Labov,et al.  Narrative analysis: Oral versions of personal experience. , 1997 .

[7]  Chris Callison-Burch,et al.  Fast, Cheap, and Creative: Evaluating Translation Quality Using Amazon’s Mechanical Turk , 2009, EMNLP.

[8]  T. Trabasso,et al.  Constructing inferences during narrative text comprehension. , 1994, Psychological review.

[9]  Ani Nenkova,et al.  Using entity features to classify implicit discourse relations , 2010, SIGDIAL Conference.

[10]  Ellen Riloff,et al.  Automatically Producing Plot Unit Representations for Narrative Text , 2010, EMNLP.

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

[12]  Jian Su,et al.  Predicting Discourse Connectives for Implicit Discourse Relation Recognition , 2010, COLING.

[13]  A. P. Dawid,et al.  Maximum Likelihood Estimation of Observer Error‐Rates Using the EM Algorithm , 1979 .

[14]  Dan Roth,et al.  Minimally Supervised Event Causality Identification , 2011, EMNLP.

[15]  Roxana Girju,et al.  Using a Bigram Event Model to Predict Causal Potential , 2009, CICLing.

[16]  Ani Nenkova,et al.  Automatic sense prediction for implicit discourse relations in text , 2009, ACL.

[17]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[18]  Reid Swanson,et al.  Learning a Probabilistic Model of Event Sequences from Internet Weblog Stories , 2008, FLAIRS Conference.

[19]  Wendy G. Lehnert,et al.  Plot Units and Narrative Summarization , 1981, Cogn. Sci..

[20]  Cosmin Adrian Bejan,et al.  Commonsense Causal Reasoning Using Millions of Personal Stories , 2011, AAAI.

[21]  R. Swanson,et al.  Identifying Personal Stories in Millions of Weblog Entries , 2009, ICWSM 2009.

[22]  Mehwish Riaz,et al.  Another Look at Causality: Discovering Scenario-Specific Contingency Relationships with No Supervision , 2010, 2010 IEEE Fourth International Conference on Semantic Computing.

[23]  Bin Bi,et al.  Iterative Learning for Reliable Crowdsourcing Systems , 2012 .

[24]  Reid Swanson,et al.  Say Anything: Using Textual Case-Based Reasoning to Enable Open-Domain Interactive Storytelling , 2012, TIIS.

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

[26]  Hwee Tou Ng,et al.  A PDTB-styled end-to-end discourse parser , 2012, Natural Language Engineering.

[27]  Christian Chiarcos Towards the Unsupervised Acquisition of Discourse Relations , 2012, ACL.