Fluency-Guided Cross-Lingual Image Captioning
Autor: | Xirong Li, Weiyu Lan, Jianfeng Dong |
---|---|
Rok vydání: | 2017 |
Předmět: |
Closed captioning
FOS: Computer and information sciences Cross lingual Computer Science - Computation and Language business.industry Computer science InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology computer.software_genre Image (mathematics) 03 medical and health sciences Fluency 0302 clinical medicine 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering ComputingMethodologies_DOCUMENTANDTEXTPROCESSING 020201 artificial intelligence & image processing Relevance (information retrieval) Artificial intelligence business computer Computation and Language (cs.CL) Natural language processing |
Zdroj: | ACM Multimedia |
DOI: | 10.48550/arxiv.1708.04390 |
Popis: | Image captioning has so far been explored mostly in English, as most available datasets are in this language. However, the application of image captioning should not be restricted by language. Only few studies have been conducted for image captioning in a cross-lingual setting. Different from these works that manually build a dataset for a target language, we aim to learn a cross-lingual captioning model fully from machine-translated sentences. To conquer the lack of fluency in the translated sentences, we propose in this paper a fluency-guided learning framework. The framework comprises a module to automatically estimate the fluency of the sentences and another module to utilize the estimated fluency scores to effectively train an image captioning model for the target language. As experiments on two bilingual (English-Chinese) datasets show, our approach improves both fluency and relevance of the generated captions in Chinese, but without using any manually written sentences from the target language. Comment: 9 pages, 2 figures, accepted as ORAL by ACM Multimedia 2017 |
Databáze: | OpenAIRE |
Externí odkaz: |