Abstract | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2013 | EMNLP | Discourse relation,Causal reasoning,Inference,Computer science,Narrative,Artificial intelligence,Natural language processing,Contingency,Machine learning |
DocType | Volume | ISSN |
Conference | abs/1708.09497 | In Proceedings of Conference on Empirical Methods in Natural
Language Processing (EMNLP 2013) |
Citations | PageRank | References |
0 | 0.34 | 17 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhichao Hu | 1 | 1 | 1.76 |
Elahe Rahimtoroghi | 2 | 12 | 2.64 |
Larissa Munishkina | 3 | 0 | 0.68 |
Reid Swanson | 4 | 165 | 16.01 |
Marilyn A. Walker | 5 | 18 | 2.40 |