Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication
Ruize Wang | Zhongyu Wei | Ying Cheng | Piji Li | Haijun Shan | Ji Zhang | Qi Zhang | Xuanjing Huang
Proceedings of the 28th International Conference on Computational Linguistics
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. In this paper, we propose a new way for visual storytelling by introducing a topic description task to detect the global semantic context of an image stream. A story is then constructed with the guidance of the topic description. In order to combine the two generation tasks, we propose a multi-agent communication framework that regards the topic description generator and the story generator as two agents and learn them simultaneously via iterative updating mechanism. We validate our approach on VIST dataset, where quantitative results, ablations, and human evaluation demonstrate our method’s good ability in generating stories with higher quality compared to state-of-the-art methods.
從語料庫看漢語助動詞的語法特點 (The Syntactic Characteristics of Chinese Auxiliaries based on the Sinica Corpus) [In Chinese]
Proceedings of Research on Computational Linguistics Conference XIII
A Corpus-Based Statistical Approach to Automatic Book Indexing
Jyun-Sheng Chang | Tsung-Yih Tseng | Sur-Jin Ker | Ying Cheng | Huey-Chyun Chen | Shun-Der Cheng | John S. Liu
Third Conference on Applied Natural Language Processing
- Jyun-Sheng Chang 1
- Tsung-Yih Tseng 1
- Sue J. Ker 1
- Huey-Chyun Chen 1
- Shun-Der Chen 1
- show all...