ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages
Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian, Amin Banitalebi-Dehkordi, Yong Zhang
Abstract
Building multi-modal language models has been a trend in the recent years, where additional modalities such as image, video, speech, etc. are jointly learned along with natural languages (i.e., textual information). Despite the success of these multi-modal language models with different modalities, there is no existing solution for neural network architectures and natural languages. Providing neural architectural information as a new modality allows us to provide fast architecture-2-text and text-2-architecture retrieval/generation services on the cloud with a single inference. Such solution is valuable in terms of helping beginner and intermediate ML users to come up with better neural architectures or AutoML approaches with a simple text query. In this paper, we propose ArchBERT, a bi-modal model for joint learning and understanding of neural architectures and natural languages, which opens up new avenues for research in this area. We also introduce a pre-training strategy named Masked Architecture Modeling (MAM) for a more generalized joint learning. Moreover, we introduce and publicly release two new bi-modal datasets for training and validating our methods. The ArchBERT’s performance is verified through a set of numerical experiments on different downstream tasks such as architecture-oriented reasoning, question answering, and captioning (summarization). Datasets, codes, and demos are available as supplementary materials.- Anthology ID:
- 2023.conll-1.7
- Volume:
- Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Jing Jiang, David Reitter, Shumin Deng
- Venue:
- CoNLL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 87–107
- Language:
- URL:
- https://aclanthology.org/2023.conll-1.7
- DOI:
- 10.18653/v1/2023.conll-1.7
- Cite (ACL):
- Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian, Amin Banitalebi-Dehkordi, and Yong Zhang. 2023. ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages. In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pages 87–107, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages (Akbari et al., CoNLL 2023)
- PDF:
- https://preview.aclanthology.org/fix_video/2023.conll-1.7.pdf