| Challenge: | Multimodal approaches to object recognition ground adjectives and nouns from text using comparative adjectives. |
| Approach: | They propose a new paradigm of grounding comparative adjectives within the realm of color descriptions by using a vector model. |
| Outcome: | The proposed model generates representations of comparative adjectives with an average accuracy of 0.65 cosine similarity to the desired direction of change. |
Similar Papers
Grounding learning of modifier dynamics: An application to color naming (D19-1)
Copied to clipboard
| Challenge: | Existing models for grounding are unable to understand modified color expressions, such as “light blue”. |
| Approach: | They propose a model that learns more complex transformations in RGB space and a hard ensemble model that selects a color space depending on the modifier-color pair. |
| Outcome: | The proposed model performs better in the HSV color space than the state-of-the-art model. |
Knowledge Supports Visual Language Grounding: A Case Study on Colour Terms (2020.acl-main)
Copied to clipboard
| Challenge: | In human cognition, world knowledge supports the perception of object colours . a lot of recent work in Language & Vision has looked at grounding language in real-world sensory information. |
| Approach: | They propose to integrate visual information and object-specific knowledge via hard-coded or learned fusion to improve visual grounding of colour terms in realistic objects. |
| Outcome: | The proposed models outperform a baseline model that predicts colour terms solely from visual inputs but show interesting differences when predicting atypical colours of so-called colour diagnostic objects. |
Learning Visually Grounded Sentence Representations (N18-1)
Copied to clipboard
| Challenge: | Unsupervised sentence representation models suffer from the grounding problem because of lack of association between symbols and external information. |
| Approach: | They train a sentence encoder to predict image features of a caption and use them as sentence representations. |
| Outcome: | The proposed model improves on word embeddings and word representations on standard benchmarks. |
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes (2024.naacl-long)
Copied to clipboard
| Challenge: | Modern neural language models (LMs) require distinctly un-human-like ways to achieve these results. |
| Approach: | They train a diverse set of LM architectures with and without auxiliary visual supervision on datasets of varying scales. |
| Outcome: | The proposed models exhibit better learning of syntactic categories, lexical relations, semantic features, word similarity and alignment with human neural representations. |
Perceptual Structure in the absence of grounding: the impact of abstractedness and subjectivity in color language for LLMs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that color perception and color language are suitable for empirically studying the problem. |
| Approach: | They propose to quantify alignment between a defined color space and a feature space in a language model by learning a mapping between embedding space and color space. |
| Outcome: | The results show that there is considerable alignment between a defined color space and the feature space defined by a language model. |
Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Neural language models (LMs) are trained on orders of magnitude more language data than human language learners receive, but without supervision from other sensory modalities that play a crucial role in human learning. |
| Approach: | They propose a grounded language learning procedure that leverages visual supervision to improve textual representations. |
| Outcome: | The proposed procedure outperforms standard language-only models in terms of learning efficiency in small and developmentally plausible data regimes and improves perplexity by around 5% on multiple language modeling tasks compared to other models trained on the same amount of text data. |
Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts (D19-1)
Copied to clipboard
| Challenge: | gradable adjectives of size are relative, i.e., determined by the context. |
| Approach: | They propose to model how the meaning of gradable adjectives of size can be learned from visually-grounded contexts by using four tasks to determine whether an object is ‘big’ or ‘small’. |
| Outcome: | The proposed model can learn subtending the meaning of size adjectives, but their performance decreases while moving from simple to more complex tasks. |
comp-syn: Perceptually Grounded Word Embeddings with Color (2020.coling-main)
Copied to clipboard
Bhargav Srinivasa Desikan, Tasker Hull, Ethan Nadler, Douglas Guilbeault, Aabir Abubakar Kar, Mark Chu, Donald Ruggiero Lo Sardo
| Challenge: | Existing approaches to natural language processing ignore embodied sensory aspects of language. |
| Approach: | They propose a Python package that provides word embeddings based on Google Image search results. |
| Outcome: | The proposed package provides word embeddings based on the color distributions of Google Image search results. |
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples (C18-1)
Copied to clipboard
| Challenge: | Existing frameworks for grounding distributional representations of texts on the visual domain are limited . effective and efficient grounding of distributional embeddings remains challenging . |
| Approach: | They propose to ground distributional representations of texts on the visual domain using visual-semantic embeddings. |
| Outcome: | The proposed model improves on a diverse set of downstream tasks and defends known-type adversarial attacks. |
Probing Contextual Language Models for Common Ground with Visual Representations (2021.naacl-main)
Copied to clipboard
| Challenge: | Contextual language models have attracted great interest in probing what is encoded in their representations. |
| Approach: | They propose a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. |
| Outcome: | The proposed model outperforms text-only language models in instance retrieval, but underperform humans. |