Word List
Research on word lists, or more broadly, the relationship between language and other data modalities, focuses on leveraging the power of words to enhance various applications. Current efforts center on using large language models (LLMs) and other deep learning architectures to analyze and generate text for tasks such as improving the interpretability of AI systems, predicting article impact, and even controlling autonomous vehicles via natural language commands. This research is significant because it bridges the gap between human-understandable language and complex data representations, leading to more transparent, efficient, and user-friendly AI systems across diverse fields.
Papers
Neural spell-checker: Beyond words with synthetic data generation
Matej Klemen, Martin Božič, Špela Arhar Holdt, Marko Robnik-Šikonja
From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes
Zébulon Goriely, Richard Diehl Martinez, Andrew Caines, Lisa Beinborn, Paula Buttery
Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval
Yuanmin Tang, Jing Yu, Keke Gai, Jiamin Zhuang, Gaopeng Gou, Gang Xiong, Qi Wu
The Scene Language: Representing Scenes with Programs, Words, and Embeddings
Yunzhi Zhang, Zizhang Li, Matt Zhou, Shangzhe Wu, Jiajun Wu