@inproceedings{akbari-etal-2023-archbert,
title = "{A}rch{BERT}: Bi-Modal Understanding of Neural Architectures and Natural Languages",
author = "Akbari, Mohammad and
Ranjbar Alvar, Saeed and
Kamranian, Behnam and
Banitalebi-Dehkordi, Amin and
Zhang, Yong",
editor = "Jiang, Jing and
Reitter, David and
Deng, Shumin",
booktitle = "Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.conll-1.7/",
doi = "10.18653/v1/2023.conll-1.7",
pages = "87--107",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akbari-etal-2023-archbert">
<titleInfo>
<title>ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Akbari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Ranjbar Alvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Kamranian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amin</namePart>
<namePart type="family">Banitalebi-Dehkordi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Reitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shumin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">akbari-etal-2023-archbert</identifier>
<identifier type="doi">10.18653/v1/2023.conll-1.7</identifier>
<location>
<url>https://aclanthology.org/2023.conll-1.7/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>87</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages
%A Akbari, Mohammad
%A Ranjbar Alvar, Saeed
%A Kamranian, Behnam
%A Banitalebi-Dehkordi, Amin
%A Zhang, Yong
%Y Jiang, Jing
%Y Reitter, David
%Y Deng, Shumin
%S Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F akbari-etal-2023-archbert
%X 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.
%R 10.18653/v1/2023.conll-1.7
%U https://aclanthology.org/2023.conll-1.7/
%U https://doi.org/10.18653/v1/2023.conll-1.7
%P 87-107
Markdown (Informal)
[ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages](https://aclanthology.org/2023.conll-1.7/) (Akbari et al., CoNLL 2023)
ACL