Corpus ID: 49297559

Multimodal Grounding for Language Processing

  title={Multimodal Grounding for Language Processing},
  author={Lisa Beinborn and Teresa Botschen and Iryna Gurevych},
  • Lisa Beinborn, Teresa Botschen, Iryna Gurevych
  • Published 2018
  • Computer Science
  • ArXiv
  • 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… CONTINUE READING
    G3raphGround: Graph-Based Language Grounding
    • 8
    • PDF
    Semantic Drift in Multilingual Representations
    • 5
    • PDF
    Using Grounded Word Representations to Study Theories of Lexical Concepts
    Uni- and Multimodal and Structured Representations for Modeling Frame Semantics
    Graph-based language grounding
    The Fluidity of Concept Representations in Human Brain Signals


    Publications referenced by this paper.
    Multimodal Distributional Semantics
    • 603
    • Highly Influential
    • PDF
    Distributional Semantics in Technicolor
    • 293
    • PDF
    Natural Language Processing (Almost) from Scratch
    • 5,478
    • PDF
    Glove: Global Vectors for Word Representation
    • 14,712
    • PDF
    Visual Information in Semantic Representation
    • 109
    • PDF
    Efficient Estimation of Word Representations in Vector Space
    • 15,153
    • PDF
    Grounded Compositional Semantics for Finding and Describing Images with Sentences
    • 681
    • PDF
    Grounded Models of Semantic Representation
    • 81
    • Highly Influential
    • PDF
    SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation
    • 841
    • PDF