Story Comprehension for Predicting What Happens Next

By Snigdha Chaturvedi, Haoruo Peng, Dan Roth. 2017

109 citations recorded by the source corpus.

Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense. In this paper, we present a story comprehension model that explores three distinct semantic aspects: (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 stories by inquiring if, like humans, it can develop an expectation of what will happen next in a given story. Specifically, we use it to predict the correct ending of a given short story from possible alternatives. The model uses a hidden variable to weigh the semantic aspects in the context of the story. Our experiments demonstrate the potential of our approach to characterize these semantic aspects, and the strength of the hidden variable based approach. The model outperforms the state-of-the-art approaches and achieves best results on a publicly available dataset.

Subfields: Artificial Intelligence, Natural Language Processing, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Prompting & Reasoning

Citations in the corpus

MERLOT: Multimodal Neural Script Knowledge Models (2021, methodology): “[20] For the unsupervised scrambling of visual stories task, we did not do any ﬁnetuning on the SIND dataset [33, 50, 2].”
Story Ending Selection by Finding Hints From Pairwise Candidate Endings (2019, unknown): “HCM [22] designed linguistic features over multiple semantic aspects to select correct endings.”
A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task (2018, methodology): “HCM (Chaturvedi et al., 2017) trained a joint model with feature engineering to obtain representations of event sequence, sentiment, and topic from validation set and a hidden variable approach as a voter, thereby obtaining 77.6%.”
Tackling the Story Ending Biases in The Story Cloze Test (2018, background): “The results show that the top-performing SCT system on the the leaderboard 1 (Chaturvedi et al., 2017) fails to keep up the performance on our new dataset.”
Joint Constrained Learning for Event-Event Relation Extraction (2020, background): “This is not only at the core of text understanding, but is also beneﬁcial to various applications such as question answering (Khashabi et al., 2018), narrative prediction (Chaturvedi et al., 2017), timeline construction (Do et al., 2012a) and summarization (Daum´e III and Marcu, 2006).”
Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training (2018, methodology): “Chaturvedi et al. (2017) explored three distinct semantic aspects including sequence of events, emotional trajectory and plot consistency, and used a hidden variable coherence model to join these aspects together.”
Incorporating Structured Commonsense Knowledge in Story Completion (2018, methodology): “Some works also exploit information such as sentiment and topic words (Chaturvedi et al. 2017) and event frames (Li et al.”