Visual Commonsense Reasoning (VCR) is a large-scale dataset for cognition-level visual understanding. Given a challenging question about an image, machines need to present two sub-tasks: answer correctly and provide a rationale justifying its answer. The VCR dataset contains over 212K (training), 26K (validation) and 25K (testing) questions, answers and rationales derived from 110K movie scenes. Source: Visual Commonsense R-CNN Image Source: From Recognition to Cognition: Visual Commonsense Reasoning
e-SNLI-VE is a large VL (vision-language) dataset with NLEs (natural language explanations) with over 430k instances for which the explanations rely on the image content. It has been built by merging the explanations from e-SNLI and the image-sentence pairs from SNLI-VE.
WHOOPS! Is a dataset and benchmark for visual commonsense. The dataset is comprised of purposefully commonsense-defying images created by designers using publicly-available image generation tools like Midjourney. It contains commonsense-defying image from a wide range of reasons, deviations from expected social norms and everyday knowledge.
The ability to recognize analogies is fundamental to human cognition. Existing benchmarks to test word analogy do not reveal the underneath process of analogical reasoning of neural models. Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR). Our benchmark consists of 1,655 (in Chinese) and 1,251 (in English) problems sourced from the Civil Service Exams, which require intensive background knowledge to solve. More importantly, we design a free-text explanation scheme to explain whether an analogy should be drawn, and manually annotate them for each and every question and candidate answer.
CLEVR-X is a dataset that extends the CLEVR dataset with natural language explanations in the context of VQA. It consists of 3.6 million natural language explanations for 850k question-image pairs. For each image-question pair in the CLEVR dataset, CLEVR-X contains multiple structured textual explanations which are derived from the original scene graphs. By construction, the CLEVR-X explanations are correct and describe the reasoning and visual information that is necessary to answer a given question. The CLEVR-X dataset consists of: - A training set of 2,401,275 natural language explanations for 70,000 images. - A validation set of 599,711 natural language explanations for 14,000 images. - A test set of 644,151 natural language explanations for 15,000 images.
E-ReDial is a conversational recommender system dataset with high-quality explanations. It consists of 756 dialogues with 12,003 utterances, each with 15.9 turns on average. 2,058 high-quality explanations are included, each with 79.2 tokens on average.
Can language models read biomedical texts and explain the biomedical mechanisms discussed? In this work we introduce a biomedical mechanism summarization task. Biomedical studies often investigate the mechanisms behind how one entity (e.g., a protein or a chemical) affects another in a biological context. The abstracts of these publications often include a focused set of sentences that present relevant supporting statements regarding such relationships, associated experimental evidence, and a concluding sentence that summarizes the mechanism underlying the relationship. We leverage this structure and create a summarization task, where the input is a collection of sentences and the main entities in an abstract, and the output includes the relationship and a sentence that summarizes the mechanism. Using a small amount of manually labeled mechanism sentences, we train a mechanism sentence classifier to filter a large biomedical abstract collection and create a summarization dataset with 22k instances. We also introduce conclusion sentence generation as a pretraining task with 611k instances. We benchmark the performance of large bio-domain language models. We find that while the pretraining task help improves performance, the best model produces acceptable mechanism outputs in only 32% of the instances, which shows the task presents significant challenges in biomedical language understanding and summarization.
Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). We introduce SpanEx, a multi-annotator dataset of human-annotated span interaction explanations for two NLU tasks: NLI and FC. SpanEx - consists of 7071 instances annotated for span interactions. - the first dataset with human phrase-level interaction explanations with explicit labels for interaction types. - annotated by three annotators, which opens new avenues for studies of human explanation agreement -- an understudied area in the explainability literature.