comp-syn: Perceptually Grounded Word Embeddings with Color (2020.coling-main)

Copied to clipboard

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.

Similar Papers

A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images (D18-1)

Copied to clipboard

Challenge: Existing approaches combine language and perception to infer word embeddings . however, the embeddables produced by such models do not reflect the actual word representations.
Approach: They propose a probabilistic model that integrates linguistic and perceptual inputs to explain observed word-context pairs in a text corpus.
Outcome: The proposed model achieves competitive or stronger results on tasks of assessing pairwise word similarity and image/caption retrieval compared to other state-of-the-art models.
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.
Word2Sense: Sparse Interpretable Word Embeddings (P19-1)

Copied to clipboard

Challenge: Word2Sense embeddings are interpretable, but they are sparse and fast to compute . a unitary rotation can be applied to many of these embeddables retaining their utility for computational tasks while changing the values of individual coordinates.
Approach: They propose an unsupervised method to generate Word2Sense word embeddings that are interpretable.
Outcome: The proposed method compares well with other unsupervised word embeddings on NLP tasks.
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.
Uncovering Visual-Semantic Psycholinguistic Properties from the Distributional Structure of Text Embedding Space (2025.acl-long)

Copied to clipboard

Challenge: Imageability and concreteness are psycholinguistic properties that link visual and semantic spaces.
Approach: They propose an unsupervised measure that quantifies sharpness of peaks in an image-caption dataset.
Outcome: The proposed method is more robust than existing methods and predicts these properties for classification.
Advances in Pre-Training Distributed Word Representations (L18-1)

Copied to clipboard

Challenge: Pre-trained word representations are a building block of many Natural Language Processing and Machine Learning applications.
Approach: They propose to combine known tricks and a set of publicly available pre-trained word vector representations to train high-quality representations.
Outcome: The proposed models outperform the current state of the art on a number of tasks while maintaining a high training speed to scale to massive amount of data.
‘Lighter’ Can Still Be Dark: Modeling Comparative Color Descriptions (P18-2)

Copied to clipboard

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.
PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing word embeddings assume fixed finite-size vocabularies, hindering their ability to provide useful word representations for out-of-vocaulary words.
Approach: They propose a model that generalizes word embeddings without extra contextual information . they use the spellings of words to model subword segmentation and compute subword-based compositional word embeds.
Outcome: The proposed model can generate meaningful subword segmentations without any source of explicit morphological knowledge.
Exploring Category Structure with Contextual Language Models and Lexical Semantic Networks (2023.eacl-main)

Copied to clipboard

Challenge: Recent work on word embeddings reports low correlations with human ratings . contextual language models (CLMs) have been successful in acquiring semantic and world knowledge.
Approach: They propose to use BERT to probe contextual language models for predicting typicality scores.
Outcome: The proposed methods improve on previous studies on word embeddings and their ability to predict typicality scores.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations