TextOnly: A Unified Function Portal for Text-Related Functions on Smartphones
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912551288176640 |
|---|---|
| author | Tu, Minghao Yu, Chun Shen, Xiyuan Zheng, Zhi Chen, Li Shi, Yuanchun |
| author_facet | Tu, Minghao Yu, Chun Shen, Xiyuan Zheng, Zhi Chen, Li Shi, Yuanchun |
| contents | Text boxes serve as portals to diverse functionalities in today's smartphone applications. However, when it comes to specific functionalities, users always need to navigate through multiple steps to access particular text boxes for input. We propose TextOnly, a unified function portal that enables users to access text-related functions from various applications by simply inputting text into a sole text box. For instance, entering a restaurant name could trigger a Google Maps search, while a greeting could initiate a conversation in WhatsApp. Despite their brevity, TextOnly maximizes the utilization of these raw text inputs, which contain rich information, to interpret user intentions effectively. TextOnly integrates large language models(LLM) and a BERT model. The LLM consistently provides general knowledge, while the BERT model can continuously learn user-specific preferences and enable quicker predictions. Real-world user studies demonstrated TextOnly's effectiveness with a top-1 accuracy of 71.35%, and its ability to continuously improve both its accuracy and inference speed. Participants perceived TextOnly as having satisfactory usability and expressed a preference for TextOnly over manual executions. Compared with voice assistants, TextOnly supports a greater range of text-related functions and allows for more concise inputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16926 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TextOnly: A Unified Function Portal for Text-Related Functions on Smartphones Tu, Minghao Yu, Chun Shen, Xiyuan Zheng, Zhi Chen, Li Shi, Yuanchun Human-Computer Interaction Artificial Intelligence Text boxes serve as portals to diverse functionalities in today's smartphone applications. However, when it comes to specific functionalities, users always need to navigate through multiple steps to access particular text boxes for input. We propose TextOnly, a unified function portal that enables users to access text-related functions from various applications by simply inputting text into a sole text box. For instance, entering a restaurant name could trigger a Google Maps search, while a greeting could initiate a conversation in WhatsApp. Despite their brevity, TextOnly maximizes the utilization of these raw text inputs, which contain rich information, to interpret user intentions effectively. TextOnly integrates large language models(LLM) and a BERT model. The LLM consistently provides general knowledge, while the BERT model can continuously learn user-specific preferences and enable quicker predictions. Real-world user studies demonstrated TextOnly's effectiveness with a top-1 accuracy of 71.35%, and its ability to continuously improve both its accuracy and inference speed. Participants perceived TextOnly as having satisfactory usability and expressed a preference for TextOnly over manual executions. Compared with voice assistants, TextOnly supports a greater range of text-related functions and allows for more concise inputs. |
| title | TextOnly: A Unified Function Portal for Text-Related Functions on Smartphones |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2508.16926 |