The possible consequences for the same context may vary depending on the situation we refer to. However, current studies in natural language processing do not focus on situated commonsense reasoning under multiple possible scenarios. This study frames this task by asking multiple questions with the same set of possible endings as candidate answers, given a short story text. Our resulting dataset, Possible Stories, consists of more than 4.5K questions over 1.3K story texts in English. We discover that even current strong pretrained language models struggle to answer the questions consistently, highlighting that the highest accuracy in an unsupervised setting (60.2%) is far behind human accuracy (92.5%). Through a comparison with existing datasets, we observe that the questions in our dataset contain minimal annotation artifacts in the answer options. In addition, our dataset includes examples that require counterfactual reasoning, as well as those requiring readers’ reactions and fictional information, suggesting that our dataset can serve as a challenging testbed for future studies on situated commonsense reasoning.

With the widespread use of social media, online hate is increasing, and microaggressions are receiving attention. We explore the potential for using pretrained language models to automatically generate messages that combat the associated offensive texts. Specifically, we focus on using prompting to steer model generation as it requires less data and computation than fine-tuning. We also propose a human evaluation perspective; offensiveness, stance, and informativeness. After obtaining 306 counterspeech and 42 microintervention messages generated by GPT-2, 3, Neo, we conducted a human evaluation using Amazon Mechanical Turk. The results indicate the potential of using prompting in the proposed generation task. All the generated texts along with the annotation are published to encourage future research on countering hate and microaggressions online.

This paper introduces a multi-lingual database containing translated texts of COVID-19 mythbusters. The database has translations into 115 languages as well as the original English texts, of which the original texts are published by World Health Organization (WHO). This paper then presents preliminary analyses on latin-alphabet-based texts to see the potential of the database as a resource for multilingual linguistic analyses. The analyses on latin-alphabet-based texts gave interesting insights into the resource. While the amount of translated texts in each language was small, character bi-grams with normalization (lowercasing and removal of diacritics) was turned out to be an effective proxy for measuring the similarity of the languages, and the affinity ranking of language pairs could be obtained. Additionally, the hierarchical clustering analysis is performed using the character bigram overlap ratio of every possible pair of languages. The result shows the cluster of Germanic languages, Romance languages, and Southern Bantu languages. In sum, the multilingual database not only offers fixed set of materials in numerous languages, but also serves as a preliminary tool to identify the language family using text-based similarity measure of bigram overlap ratio.

This research paper reports on the generation of the first Drenjongke corpus based on texts taken from a phrase book for beginners, written in the Tibetan script. A corpus of sentences was created after correcting errors in the text scanned through optical character reading (OCR). A total of 34 Part-of-Speech (PoS) tags were defined based on manual annotation performed by the three authors, one of whom is a native speaker of Drenjongke. The first corpus of the Drenjongke language comprises 275 sentences and 1379 tokens, which we plan to expand with other materials to promote further studies of this language.