Multimodal Grounding for Language Processing
arXiv:1806.06371
Abstract
This survey discusses how recent developments in multimodal processing facilitate conceptual grounding of language. We categorize the information flow in multimodal processing with respect to cognitive models of human information processing and analyze different methods for combining multimodal representations. Based on this methodological inventory, we discuss the benefit of multimodal grounding for a variety of language processing tasks and the challenges that arise. We particularly focus on multimodal grounding of verbs which play a crucial role for the compositional power of language.
arXiv commentThe paper has been published in the Proceedings of the 27 Conference of Computational Linguistics. Please refer to this version for citations: https://www.aclweb.org/anthology/papers/C/C18/C18-1197/
References in corpus (11)
- Efficient Estimation of Word Representations in Vector Space
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Natural Language Processing (almost) from Scratch
- Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
- Zero-Shot Learning Through Cross-Modal Transfer
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- Modulating early visual processing by language
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Grounded Language Learning in a Simulated 3D World
- Gated-Attention Architectures for Task-Oriented Language Grounding
- The automatic creation of concept maps from documents written using morphologically rich languages