Self-Enhancing Multi-filter Sequence-to-Sequence Model

TL;DR

This paper introduces a multi-filter sequence-to-sequence model with a self-enhancing mechanism that uses reinforcement learning to optimize clustering, improving performance on NLP tasks like semantic parsing and translation.

Contribution

It proposes a novel self-enhancing multi-filter encoder-decoder model that addresses heterogeneity in representations through clustering and reinforcement learning.

Findings

Outperforms benchmarks by at least 5% in NLP tasks.

Self-enhancing mechanism improves performance by over 10%.

Positive correlation between clustering quality and model performance.

Abstract

Representation learning is important for solving sequence-to-sequence problems in natural language processing. Representation learning transforms raw data into vector-form representations while preserving their features. However, data with significantly different features leads to heterogeneity in their representations, which may increase the difficulty of convergence. We design a multi-filter encoder-decoder model to resolve the heterogeneity problem in sequence-to-sequence tasks. The multi-filter model divides the latent space into subspaces using a clustering algorithm and trains a set of decoders (filters) in which each decoder only concentrates on the features from its corresponding subspace. As for the main contribution, we design a self-enhancing mechanism that uses a reinforcement learning algorithm to optimize the clustering algorithm without additional training data. We run semantic parsing and machine translation experiments to indicate that the proposed model can outperform most benchmarks by at least 5\%. We also empirically show the self-enhancing mechanism can improve performance by over 10\% and provide evidence to demonstrate the positive correlation between the model's performance and the latent space clustering.