Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks
Abstract
Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of natural language processing and computer vision tasks, including language modeling, natural language inference, and image classification. In this work, we explore the applicability of a SOTA NAS algorithm, Efficient Neural Architecture Search (ENAS) (Pham et al., 2018) to two sentence pair tasks, paraphrase detection and semantic textual similarity. We use ENAS to perform a micro-level search and learn a task-optimized RNN cell architecture as a drop-in replacement for an LSTM. We explore the effectiveness of ENAS through experiments on three datasets (MRPC, SICK, STS-B), with two different models (ESIM, BiLSTM-Max), and two sets of embeddings (Glove, BERT). In contrast to prior work applying ENAS to NLP tasks, our results are mixed -- we find that ENAS architectures sometimes, but not always, outperform LSTMs and perform similarly to random architecture search.
Cite
@article{arxiv.2010.04249,
title = {Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks},
author = {Ansel MacLaughlin and Jwala Dhamala and Anoop Kumar and Sriram Venkatapathy and Ragav Venkatesan and Rahul Gupta},
journal= {arXiv preprint arXiv:2010.04249},
year = {2020}
}