Visuallly Grounded Generation of Entailments from Premises
This addresses the problem of multimodal natural language inference generation for AI and NLP researchers, but it is incremental as it builds on existing NLI tasks with minor improvements.
The paper tackled generating entailments (hypotheses) from premises in a multimodal setting using images and/or descriptions, showing that entailments can be generated successfully and multimodal models slightly outperform unimodal ones.
Natural Language Inference (NLI) is the task of determining the semantic relationship between a premise and a hypothesis. In this paper, we focus on the {\em generation} of hypotheses from premises in a multimodal setting, to generate a sentence (hypothesis) given an image and/or its description (premise) as the input. The main goals of this paper are (a) to investigate whether it is reasonable to frame NLI as a generation task; and (b) to consider the degree to which grounding textual premises in visual information is beneficial to generation. We compare different neural architectures, showing through automatic and human evaluation that entailments can indeed be generated successfully. We also show that multimodal models outperform unimodal models in this task, albeit marginally.