EMBODIED QUESTION ANSWERING IN ROBOTIC ENVIRONMENT Automatic generation of a synthetic question-answer data-set
| Aruqi, Ali | ||
| University of Gothenburg / Department of Philosophy,Lingustics and Theory of Science | eng | |
| Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori | swe | |
| 2021-11-12T07:35:44Z | ||
| 2021-11-12T07:35:44Z | ||
| 2021-11-12 | ||
| Embodied question answering is the task of asking a robot about objects in a 3D environment. The robot has to navigate the environment, find the entities in question, and then stop to answer the question. The answering system consists of navigation and visual-question-answering components. The agent is trained on a synthetic data-set of question-answers and navigational paths called EQA-MP3D. Each question in the data-set is an executable function that could be run in the environment to yield an answer. EQA-MP3D includes only two types of questions, color and location questions. The type of questions asked could be considered unnatural, and we observe that the question-answers contain biases. Our work extends the data-set by automatically generating size and spatial questions. We generate a total of 19 207 question-answers for training and 3 186 question-answers for validation. Our data extension is intended to train the system to answer more question types and enhance the system’s overall ability to perform the task. | sv | |
| http://hdl.handle.net/2077/70001 | ||
| eng | sv | |
| HumanitiesTheology | ||
| Embodied Question Answering | sv | |
| Question Generation | sv | |
| Spatial Relations | sv | |
| Synthetic Data-sets | sv | |
| Multi-Modality | sv | |
| EMBODIED QUESTION ANSWERING IN ROBOTIC ENVIRONMENT Automatic generation of a synthetic question-answer data-set | sv | |
| Text | ||
| Student essay | ||
| H2 |