Recently, large pre-trained language models (LLMs) have demonstrated superior language understanding abilities, including zero-shot causal reasoning. However, it is unclear to what extent their capabilities are similar to human ones. We here study the processing of an event $B$ in a script-based story, which causally depends on a previous event $A$. In our manipulation, event $A$ is stated, negated, or omitted in an earlier section of the text. We first conducted a self-paced reading experiment, which showed that humans exhibit significantly longer reading times when causal conflicts exist ($\neg A \rightarrow B$) than under logical conditions ($A \rightarrow B$). However, reading times remain similar when cause A is not explicitly mentioned, indicating that humans can easily infer event B from their script knowledge. We then tested a variety of LLMs on the same data to check to what extent the models replicate human behavior. Our experiments show that 1) only recent LLMs, like GPT-3 or Vicuna, correlate with human behavior in the $\neg A \rightarrow B$ condition. 2) Despite this correlation, all models still fail to predict that $nil \rightarrow B$ is less surprising than $\neg A \rightarrow B$, indicating that LLMs still have difficulties integrating script knowledge. Our code and collected data set are available at https://github.com/tony-hong/causal-script.

Script knowledge consists of detailed information on everyday activities. Such information is often taken for granted in text and needs to be inferred by readers. Therefore, script knowledge is a central component to language comprehension. Previous work on representing scripts is mostly based on extensive manual work or limited to scenarios that can be found with sufficient redundancy in large corpora. We introduce the task of scenario detection, in which we identify references to scripts. In this task, we address a wide range of different scripts (200 scenarios) and we attempt to identify all references to them in a collection of narrative texts. We present a first benchmark data set and a baseline model that tackles scenario detection using techniques from topic segmentation and text classification.

Statistical script learning is an effective way to acquire world knowledge which can be used for commonsense reasoning. Statistical script learning induces this knowledge by observing event sequences generated from texts. The learned model thus can predict subsequent events, given earlier events. Recent approaches rely on learning event embeddings which capture script knowledge. In this work, we suggest a general learning model–Featured Event Embedding Learning (FEEL)–for injecting event embeddings with fine grained information. In addition to capturing the dependencies between subsequent events, our model can take into account higher level abstractions of the input event which help the model generalize better and account for the global context in which the event appears. We evaluated our model over three narrative cloze tasks, and showed that our model is competitive with the most recent state-of-the-art. We also show that our resulting embedding can be used as a strong representation for advanced semantic tasks such as discourse parsing and sentence semantic relatedness.

Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can predict upcoming discourse referents based on linguistic knowledge alone vs. linguistic knowledge jointly with common-sense knowledge in the form of scripts. We find that script knowledge significantly improves model estimates of human predictions. In a second study, we test the highly controversial hypothesis that predictability influences referring expression type but do not find evidence for such an effect.