We introduce a collection of recognizing textual entailment (RTE) datasets focused on figurative language. We leverage five existing datasets annotated for a variety of figurative language -- simile, metaphor, and irony -- and frame them into over 12,500 RTE examples.We evaluate how well state-of-the-art models trained on popular RTE datasets capture different aspects of figurative language. Our results and analyses indicate that these models might not sufficiently capture figurative language, struggling to perform pragmatic inference and reasoning about world knowledge. Ultimately, our datasets provide a challenging testbed for evaluating RTE models.

"Framing" involves the positive or negative presentation of an argument or issue depending on the audience and goal of the speaker (Entman 1983). Differences in lexical framing, the focus of our work, can have large effects on peoples' opinions and beliefs. To make progress towards reframing arguments for positive effects, we create a dataset and method for this task. We use a lexical resource for "connotations" to create a parallel corpus and propose a method for argument reframing that combines controllable text generation (positive connotation) with a post-decoding entailment component (same denotation). Our results show that our method is effective compared to strong baselines along the dimensions of fluency, meaning, and trustworthiness/reduction of fear.

Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion. We posit that many of the problems of story generation can be addressed via high-quality content planning, and present a system that focuses on how to learn good plot structures to guide story generation. We utilize a plot-generation language model along with an ensemble of rescoring models that each implement an aspect of good story-writing as detailed in Aristotle's Poetics. We find that stories written with our more principled plot-structure are both more relevant to a given prompt and higher quality than baselines that do not content plan, or that plan in an unprincipled way.

We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence. Our method employs a retrieve-and-edit framework to instantiate two major characteristics of sarcasm: reversal of valence and semantic incongruity with the context which could include shared commonsense or world knowledge between the speaker and the listener. While prior works on sarcasm generation predominantly focus on context incongruity, we show that combining valence reversal and semantic incongruity based on the commonsense knowledge generates sarcasm of higher quality. Human evaluation shows that our system generates sarcasm better than human annotators 34% of the time, and better than a reinforced hybrid baseline 90% of the time.

Understanding cross-cultural differences is an important application of natural language understanding. This problem is difficult due to the relativism between cultures. We present a computational approach to learn cultural models that encode the general opinions and values of cultures from multi-lingual Wikipedia. Specifically, we assume a language is a symbol of a culture and different languages represent different cultures. Our model can automatically identify statements that potentially reflect cultural differences. Experiments on English and Chinese languages show that on a held out set of diverse topics, including marriage, gun control, democracy, etc., our model achieves high correlation with human judgements regarding within-culture values and cultural differences.