2019/10/24 by An Yan, Xin Wang, Xin Eric Wang +8 · 1 citation
Computer Science · #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Robotics (cs.RO) #cs.CL #cs.CV #cs.RO
paper · pdf · doi:10.48550/arxiv.1910.11301
openalex publication_date 2019/10/24 · arxiv created 2020/12/06 · arxiv updated 2020/12/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics. But the dominant language is English, according to previous studies on vision-language navigation (VLN). To go beyond English and serve people speaking different languages, we collect a bilingual Room-to-Room (BL-R2R) dataset, extending the original benchmark with new Chinese instructions. Based on this newly introduced dataset, we study how an agent can be trained on existing English instructions but navigate effectively with another language under a zero-shot learning scenario. Without any training data of the target language, our model shows competitive results even compared to a model with full access to the target language training data. Moreover, we investigate the transferring ability of our model when given a certain amount of target language training data.