Weight-sharing neural architecture search: A battle to shrink the optimization gap

L Xie, X Chen, K Bi, L Wei, Y Xu, L Wang… - ACM Computing …, 2021 - dl.acm.org
Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Meta learning for natural language processing: A survey

H Lee, SW Li, NT Vu - arXiv preprint arXiv:2205.01500, 2022 - arxiv.org
Deep learning has been the mainstream technique in natural language processing (NLP)
area. However, the techniques require many labeled data and are less generalizable across …

Nas-bench-nlp: neural architecture search benchmark for natural language processing

N Klyuchnikov, I Trofimov, E Artemova… - IEEE …, 2022 - ieeexplore.ieee.org
Neural Architecture Search (NAS) is a promising and rapidly evolving research area.
Training a large number of neural networks requires an exceptional amount of …

Semeval-2022 Task 1: CODWOE--Comparing Dictionaries and Word Embeddings

T Mickus, K Van Deemter, M Constant… - arXiv preprint arXiv …, 2022 - arxiv.org
Word embeddings have advanced the state of the art in NLP across numerous tasks.
Understanding the contents of dense neural representations is of utmost interest to the …

Leveraging similar users for personalized language modeling with limited data

C Welch, C Gu, JK Kummerfeld… - Proceedings of the …, 2022 - aclanthology.org
Personalized language models are designed and trained to capture language patterns
specific to individual users. This makes them more accurate at predicting what a user will …

Compositional demographic word embeddings

C Welch, JK Kummerfeld, V Pérez-Rosas… - arXiv preprint arXiv …, 2020 - arxiv.org
Word embeddings are usually derived from corpora containing text from many individuals,
thus leading to general purpose representations rather than individually personalized …

Ranknas: Efficient neural architecture search by pairwise ranking

C Hu, C Wang, X Ma, X Meng, Y Li, T Xiao… - arXiv preprint arXiv …, 2021 - arxiv.org
This paper addresses the efficiency challenge of Neural Architecture Search (NAS) by
formulating the task as a ranking problem. Previous methods require numerous training …

Neural architecture search for resource constrained hardware devices: A survey

Y Yang, J Zhan, W Jiang, Y Jiang… - IET Cyber‐Physical …, 2023 - Wiley Online Library
With the emergence of powerful and low‐energy Internet of Things devices, deep learning
computing is increasingly applied to resource‐constrained edge devices. However, the …

Learning reliable neural networks with distributed architecture representations

Y Li, R Cao, Q He, T Xiao, J Zhu - ACM Transactions on Asian and Low …, 2023 - dl.acm.org
Neural architecture search (NAS) has shown the strong performance of learning neural
models automatically in recent years. But most NAS systems are unreliable due to the …

DORE: A Dataset For Portuguese Definition Generation

ABD Furtado, T Ranasinghe, F Blain… - arXiv preprint arXiv …, 2024 - arxiv.org
Definition modelling (DM) is the task of automatically generating a dictionary definition for a
specific word. Computational systems that are capable of DM can have numerous …