Papers by Jatin Lamba
MIMOQA: Multimodal Input Multimodal Output Question Answering (2021.naacl-main)
Copied to clipboard
| Challenge: | Multimodal research has picked up significantly in the space of question answering with the task being extended to visual question answering, charts question answering as well as multimodal input question answering. |
| Approach: | They propose a multimodal question-answering task that produces a unimodal textual output as the answer through human experiments. |
| Outcome: | The proposed framework outperforms existing frameworks on both automatic and human metrics. |