We present the results of the Shared Task on Understanding Figurative Language that we conducted as a part of the 3rd Workshop on Figurative Language Processing (FigLang 2022) at EMNLP 2022. The shared task is based on the FLUTE dataset (Chakrabarty et al., 2022), which consists of NLI pairs containing figurative language along with free text explanations for each NLI instance. The task challenged participants to build models that are able to not only predict the right label for a figurative NLI instance, but also generate a convincing free-text explanation. The participants were able to significantly improve upon provided baselines in both automatic and human evaluation settings. We further summarize the submitted systems and discuss the evaluation results.

Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a.k.a. natural language inference (NLI)). However, similar to classical RTE/NLI datasets they suffer from spurious correlations and annotation artifacts. To tackle this problem, work on NLI has built explanation-based datasets such as eSNLI, allowing us to probe whether language models are right for the right reasons. Yet no such data exists for figurative language, making it harder to assess genuine understanding of such expressions. To address this issue, we release FLUTE, a dataset of 9,000 figurative NLI instances with explanations, spanning four categories: Sarcasm, Simile, Metaphor, and Idioms. We collect the data through a Human-AI collaboration framework based on GPT-3, crowd workers, and expert annotators. We show how utilizing GPT-3 in conjunction with human annotators (novices and experts) can aid in scaling up the creation of datasets even for such complex linguistic phenomena as figurative language. The baseline performance of the T5 model fine-tuned on FLUTE shows that our dataset can bring us a step closer to developing models that understand figurative language through textual explanations.

Despite constant improvements in machine translation quality, automatic poetry translation remains a challenging problem due to the lack of open-sourced parallel poetic corpora, and to the intrinsic complexities involved in preserving the semantics, style and figurative nature of poetry. We present an empirical investigation for poetry translation along several dimensions: 1) size and style of training data (poetic vs. non-poetic), including a zero-shot setup; 2) bilingual vs. multilingual learning; and 3) language-family-specific models vs. mixed-language-family models. To accomplish this, we contribute a parallel dataset of poetry translations for several language pairs. Our results show that multilingual fine-tuning on poetic text significantly outperforms multilingual fine-tuning on non-poetic text that is 35X larger in size, both in terms of automatic metrics (BLEU, BERTScore, COMET) and human evaluation metrics such as faithfulness (meaning and poetic style). Moreover, multilingual fine-tuning on poetic data outperforms bilingual fine-tuning on poetic data.

We introduce a FEVER-like dataset COVID-Fact of 4,086 claims concerning the COVID-19 pandemic. The dataset contains claims, evidence for the claims, and contradictory claims refuted by the evidence. Unlike previous approaches, we automatically detect true claims and their source articles and then generate counter-claims using automatic methods rather than employing human annotators. Along with our constructed resource, we formally present the task of identifying relevant evidence for the claims and verifying whether the evidence refutes or supports a given claim. In addition to scientific claims, our data contains simplified general claims from media sources, making it better suited for detecting general misinformation regarding COVID-19. Our experiments indicate that COVID-Fact will provide a challenging testbed for the development of new systems and our approach will reduce the costs of building domain-specific datasets for detecting misinformation.