From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Charles, Peng, Benji, Sun, Xintian, Niu, Qian, Liu, Junyu, Chen, Keyu, Li, Ming, Feng, Pohsun, Bi, Ziqian, Liu, Ming, Zhang, Yichao, Song, Xinyuan, Fei, Cheng, Yin, Caitlyn Heqi, Yan, Lawrence KQ, He, Hongyang, Wang, Tianyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912741579554816
author Zhang, Charles
Peng, Benji
Sun, Xintian
Niu, Qian
Liu, Junyu
Chen, Keyu
Li, Ming
Feng, Pohsun
Bi, Ziqian
Liu, Ming
Zhang, Yichao
Song, Xinyuan
Fei, Cheng
Yin, Caitlyn Heqi
Yan, Lawrence KQ
He, Hongyang
Wang, Tianyang
author_facet Zhang, Charles
Peng, Benji
Sun, Xintian
Niu, Qian
Liu, Junyu
Chen, Keyu
Li, Ming
Feng, Pohsun
Bi, Ziqian
Liu, Ming
Zhang, Yichao
Song, Xinyuan
Fei, Cheng
Yin, Caitlyn Heqi
Yan, Lawrence KQ
He, Hongyang
Wang, Tianyang
contents Word embeddings and language models have transformed natural language processing (NLP) by facilitating the representation of linguistic elements in continuous vector spaces. This review visits foundational concepts such as the distributional hypothesis and contextual similarity, tracing the evolution from sparse representations like one-hot encoding to dense embeddings including Word2Vec, GloVe, and fastText. We examine both static and contextualized embeddings, underscoring advancements in models such as ELMo, BERT, and GPT and their adaptations for cross-lingual and personalized applications. The discussion extends to sentence and document embeddings, covering aggregation methods and generative topic models, along with the application of embeddings in multimodal domains, including vision, robotics, and cognitive science. Advanced topics such as model compression, interpretability, numerical encoding, and bias mitigation are analyzed, addressing both technical challenges and ethical implications. Additionally, we identify future research directions, emphasizing the need for scalable training techniques, enhanced interpretability, and robust grounding in non-textual modalities. By synthesizing current methodologies and emerging trends, this survey offers researchers and practitioners an in-depth resource to push the boundaries of embedding-based language models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05036
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models
Zhang, Charles
Peng, Benji
Sun, Xintian
Niu, Qian
Liu, Junyu
Chen, Keyu
Li, Ming
Feng, Pohsun
Bi, Ziqian
Liu, Ming
Zhang, Yichao
Song, Xinyuan
Fei, Cheng
Yin, Caitlyn Heqi
Yan, Lawrence KQ
He, Hongyang
Wang, Tianyang
Computation and Language
Word embeddings and language models have transformed natural language processing (NLP) by facilitating the representation of linguistic elements in continuous vector spaces. This review visits foundational concepts such as the distributional hypothesis and contextual similarity, tracing the evolution from sparse representations like one-hot encoding to dense embeddings including Word2Vec, GloVe, and fastText. We examine both static and contextualized embeddings, underscoring advancements in models such as ELMo, BERT, and GPT and their adaptations for cross-lingual and personalized applications. The discussion extends to sentence and document embeddings, covering aggregation methods and generative topic models, along with the application of embeddings in multimodal domains, including vision, robotics, and cognitive science. Advanced topics such as model compression, interpretability, numerical encoding, and bias mitigation are analyzed, addressing both technical challenges and ethical implications. Additionally, we identify future research directions, emphasizing the need for scalable training techniques, enhanced interpretability, and robust grounding in non-textual modalities. By synthesizing current methodologies and emerging trends, this survey offers researchers and practitioners an in-depth resource to push the boundaries of embedding-based language models.
title From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2411.05036