Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks

TL;DR

This paper investigates the application of Efficient Neural Architecture Search (ENAS) to sentence-pair tasks like paraphrase detection and semantic similarity, finding mixed results in its effectiveness compared to traditional LSTM models.

Contribution

It explores the use of ENAS for optimizing RNN cell architectures specifically for NLP sentence-pair tasks, which has not been extensively studied before.

Findings

ENAS architectures sometimes outperform LSTMs

ENAS results are similar to random search

Performance varies across datasets and models

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.