Report
MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning
| العنوان: | MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning |
|---|---|
| المؤلفون: | Cui, Wanqing, Bi, Keping, Guo, Jiafeng, Cheng, Xueqi |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language |
| الوصف: | Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge. Several studies have leveraged text retrieval to augment the models' commonsense ability. Unlike text, images capture commonsense information inherently but little effort has been paid to effectively utilize them. In this work, we propose a novel Multi-mOdal REtrieval (MORE) augmentation framework, to leverage both text and images to enhance the commonsense ability of language models. Extensive experiments on the Common-Gen task have demonstrated the efficacy of MORE based on the pre-trained models of both single and multiple modalities. Comment: Published as a conference paper at ACL Findings 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.13625 |
| رقم الانضمام: | edsarx.2402.13625 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |