ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909630782767104 |
|---|---|
| author | Barua, Deeparghya Dutta Sourove, Md Sakib Ul Rahman Fahim, Md Haider, Fabiha Shifat, Fariha Tanjim Adib, Md Tasmim Rahman Uddin, Anam Borhan Ishmam, Md Farhan Alam, Md Farhad |
| author_facet | Barua, Deeparghya Dutta Sourove, Md Sakib Ul Rahman Fahim, Md Haider, Fabiha Shifat, Fariha Tanjim Adib, Md Tasmim Rahman Uddin, Anam Borhan Ishmam, Md Farhan Alam, Md Farhad |
| contents | Visual Question Answer (VQA) poses the problem of answering a natural language question about a visual context. Bangla, despite being a widely spoken language, is considered low-resource in the realm of VQA due to the lack of proper benchmarks, challenging models known to be performant in other languages. Furthermore, existing Bangla VQA datasets offer little regional relevance and are largely adapted from their foreign counterparts. To address these challenges, we introduce a large-scale Bangla VQA dataset, ChitroJera, totaling over 15k samples from diverse and locally relevant data sources. We assess the performance of text encoders, image encoders, multimodal models, and our novel dual-encoder models. The experiments reveal that the pre-trained dual-encoders outperform other models of their scale. We also evaluate the performance of current large vision language models (LVLMs) using prompt-based techniques, achieving the overall best performance. Given the underdeveloped state of existing datasets, we envision ChitroJera expanding the scope of Vision-Language tasks in Bangla. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14991 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla Barua, Deeparghya Dutta Sourove, Md Sakib Ul Rahman Fahim, Md Haider, Fabiha Shifat, Fariha Tanjim Adib, Md Tasmim Rahman Uddin, Anam Borhan Ishmam, Md Farhan Alam, Md Farhad Computer Vision and Pattern Recognition Computation and Language Visual Question Answer (VQA) poses the problem of answering a natural language question about a visual context. Bangla, despite being a widely spoken language, is considered low-resource in the realm of VQA due to the lack of proper benchmarks, challenging models known to be performant in other languages. Furthermore, existing Bangla VQA datasets offer little regional relevance and are largely adapted from their foreign counterparts. To address these challenges, we introduce a large-scale Bangla VQA dataset, ChitroJera, totaling over 15k samples from diverse and locally relevant data sources. We assess the performance of text encoders, image encoders, multimodal models, and our novel dual-encoder models. The experiments reveal that the pre-trained dual-encoders outperform other models of their scale. We also evaluate the performance of current large vision language models (LVLMs) using prompt-based techniques, achieving the overall best performance. Given the underdeveloped state of existing datasets, we envision ChitroJera expanding the scope of Vision-Language tasks in Bangla. |
| title | ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2410.14991 |