Story Comprehension for Predicting What Happens Next

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1603–1614 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Story Comprehension for Predicting What Happens Next Snigdha Chaturvedi Haoruo Peng Dan Roth University of Illinois, Urbana-Champaign {snigdha,hpeng7,danr}@illinois.edu Abstract Automatic story comprehension is a fun- damental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human be- havior and commonsense. In this paper, we present a story comprehension model that explores three distinct semantic as- pects: (i) the sequence of events described in the story, (ii) its emotional trajectory, and (iii) its plot consistency. We judge the model’s understanding of real-world sto- ries by inquiring if, like humans, it can develop an expectation of what will hap- pen next in a given story. Specifically, we use it to predict the correct ending of a given short story from possible alterna- tives. The model uses a hidden variable to weigh the semantic aspects in the con- text of the story. Our experiments demon- strate the potential of our approach to char- acterize these semantic aspects, and the strength of the hidden variable based ap- proach. The model outperforms the state- of-the-art approaches and achieves best re- sults on a publicly available dataset. 1 Introduction Narratives are a fundamental part of human lan- guage and culture. They serve as vehicles to share experiences, information and goals. For these reasons, automatically understanding stories is an interesting but challenging task for Compu- tational Linguists (Mani, 2012). Story compre- hension involves not only an array of NLP ca- pabilities, but also some common sense knowl- edge and an understanding of normative social behavior (Charniak, 1972). Past research has focused on various aspects of story understand- Context: One day Wesley’s auntie came over to visit. He was happy to see her, because he liked to play with her. When she started to give his little sister attention, he got jealous. He got angry at his auntie and bit her hand when she wasn’t looking. Incorrect Ending: She gave him a cookie for being so nice. Correct Ending: He was scolded. Figure 1: Example from the story-cloze task: pre- dict the correct ending to a given short story out of provided options. ing such as identifying character personas (Bam- man et al., 2014; Valls-Vargas et al., 2015), inter- personal relationships (Chaturvedi, 2016), plot- patterns (Jockers, 2013), narrative structures (Fin- layson, 2012). There has also been an interest in predicting what is expected to happen next in a piece of text (Chambers and Jurafsky, 2008). Hu- man readers are good at filling-in-the-gaps or in- ferring information that is not explicitly stated in the text. However, computers are not yet able to match their performance on predicting what could be the likely next step in a given sequence of events described in a story. Recently, Mostafazadeh et al. (2016) introduced the story-cloze task for testing this ability, albeit without the aspect of language generation. This task requires choosing the correct …

Content truncated to 500 words