Counterfactual Story Reasoning and Generation

@inproceedings{Qin2019CounterfactualSR,
  title={Counterfactual Story Reasoning and Generation},
  author={Lianhui Qin and Antoine Bosselut and Ari Holtzman and Chandra Bhagavatula and Elizabeth Clark and Yejin Choi},
  booktitle={EMNLP},
  year={2019}
}
Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. [] Key Method Additionally, we include 80,115 counterfactual "branches" without a rewritten storyline to support future work on semi- or un-supervised approaches to counterfactual story rewriting. Finally, we evaluate the counterfactual rewriting capacities of several competitive baselines based on pretrained language models, and assess whether common overlap…

Figures and Tables from this paper

Unsupervised Editing for Counterfactual Stories

TLDR
EDUCAT, an editing-based unsupervised approach for counterfactual story rewriting that includes a target position detection strategy based on estimating causal effects of the what-if conditions, keeps the causal invariant parts of the story.

Sketch and Customize: A Counterfactual Story Generator

TLDR
A sketch-and-customize generation model guided by the causality implicated in the conditions and endings is proposed, which generates much better endings, as compared with the traditional sequence-to-sequence model.

SemEval-2020 Task 5: Counterfactual Recognition

TLDR
This task provides a benchmark for counterfactual recognition in natural language with two subtasks, and requires the participating systems to extract the antecedent and consequent in a givencounterfactual statement.

PASTA: A Dataset for Modeling Participant States in Narratives

The events in a narrative can be understood as a coherent whole via the underlying states of its participants. Often, these participant states are not explicitly mentioned in the narrative, left to

Rethinking the framework constructed by counterfactual functional model

TLDR
This paper proposes a mild version of the treatment-unit additivity assumption coined as M-TUA based on the damped vibration equation in physics to alleviate the strength of the constraints in the original assumptions with reasonable formal expression.

Generating Hypothetical Events for Abductive Inference

TLDR
This work proposes a multi-task model MTL to solve the Abductive NLI task, which predicts a plausible explanation by considering different possible events emerging from candidate hypotheses – events generated by LMI – and selecting the one that is most similar to the observed outcome.

Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning

TLDR
This work devise a Learning to Imagine (L2I) module, which can be seamlessly incorporated into NDR models to perform the imagination of unseen counterfactual and applies the proposed L2I to TAGOP, the state-of-the-art solution on TAT-QA, validating the rationality and effectiveness of this approach.

Paragraph-Level Commonsense Transformers with Recurrent Memory

TLDR
PARA-COMET, a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives, outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.

Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision

TLDR
This paper investigates multiple ways to automatically generate rationales using pre-trained language models, neural knowledge models, and distant supervision from related tasks, and trains generative models capable of composing explanatory rationales for unseen instances.

Connecting Attributions and QA Model Behavior on Realistic Counterfactuals

TLDR
It is found that pairwise attributions are better suited to RC than token-level attributions across these different RC settings, with the best performance coming from a modification that is proposed to an existing pairwise attribution method.
...

References

SHOWING 1-10 OF 40 REFERENCES

A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories

TLDR
A new framework for evaluating story understanding and script learning: the 'Story Cloze Test', which requires a system to choose the correct ending to a four-sentence story, and a new corpus of ~50k five- Sentence commonsense stories, ROCStories, to enable this evaluation.

Recognizing Counterfactual Thinking in Social Media Texts

TLDR
Acounterfactual tweet dataset is created and approaches for detecting counterfactuals using rule-based and supervised statistical approaches are explored, finding a combined rule- based and statistical approach yielded the best results.

ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning

TLDR
Experimental results demonstrate that multitask models that incorporate the hierarchical structure of if-then relation types lead to more accurate inference compared to models trained in isolation, as measured by both automatic and human evaluation.

SemEval-2012 Task 7: Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning

TLDR
The two systems that competed in this task as part of SemEval-2012 are described, and their results are compared to those achieved in previously published research.

Toward a Useful Concept of Causality for Lexical Semantics

TLDR
The notion of'causal complex' is introduced for a complete set of events and conditions necessary for the causal consequent to occur, and the term 'cause' is used for the makeshift, nonmonotonic notion the authors require for everyday tasks such as planning and language understanding.

Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback

TLDR
This work is the first to show that semantic parsers can be improved significantly by counterfactual learning from logged human feedback data, and devise an easy-to-use interface to collect human feedback on semantic parses.

A Theme-Rewriting Approach for Generating Algebra Word Problems

TLDR
This paper presents a text generation method called It rewriting, which edits existing human-authored narratives to change their theme without changing the underlying story, and applies it to math word problems, where it might help students stay more engaged by quickly transforming all of their homework assignments to the theme of their favorite movie without changes the math concepts that are being taught.

Statistical Script Learning with Multi-Argument Events

TLDR
Experiments on a large corpus using the task of inferring held-out events and the “narrative cloze evaluation” demonstrate that modeling multi-argument events improves predictive accuracy.

Mental models and counterfactual thoughts about what might have been

  • R. Byrne
  • Psychology, Philosophy
    Trends in Cognitive Sciences
  • 2002

Event Schema Induction with a Probabilistic Entity-Driven Model

TLDR
This paper presents the first generative model for schema induction that integrates coreference chains into learning, and matches the pipeline’s performance, and outperforms the HMM by 7 F1 points.