Accurate Word Representations with Universal Visual Guidance

Haojie Yu, Zhuosheng Zhang, hai zhao, Rui Wang, Masao Utiyama

Keywords: Natural Language Processing, Visual Representation, Multimodal Language Representation, Natural Language Understanding

Abstract: Word representation is a fundamental component in neural language understanding models. Recently, pre-trained language models (PrLMs) offer a new performant method of contextualized word representations by leveraging the sequence-level context for modeling. Although the PrLMs generally give more accurate contextualized word representations than non-contextualized models do, they are still subject to a sequence of text contexts without diverse hints for word representation from multimodality. This paper thus proposes a visual representation method to explicitly enhance conventional word embedding with multiple-aspect senses from visual guidance. In detail, we build a small-scale word-image dictionary from a multimodal seed dataset where each word corresponds to diverse related images. The texts and paired images are encoded in parallel, followed by an attention layer to integrate the multimodal representations. We show that the method substantially improves the accuracy of disambiguation. Experiments on 12 natural language understanding and machine translation tasks further verify the effectiveness and the generalization capability of the proposed approach.

One-sentence Summary: This paper proposes a visual representation method to explicitly augment conventional word embedding with multiple-aspect senses from visual guidance.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2012.15086/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=yxJD_4lL0