Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization
This addresses the issue of underutilizing prior knowledge in NLP models, offering a flexible mechanism for domain-specific applications, though it is incremental in its approach.
The paper tackled the problem of neural models ignoring external linguistic resources like WordNet or UMLS by proposing a novel weight-sharing method to incorporate domain knowledge, resulting in consistently improved performance on classification tasks compared to baselines.
A fundamental advantage of neural models for NLP is their ability to learn representations from scratch. However, in practice this often means ignoring existing external linguistic resources, e.g., WordNet or domain specific ontologies such as the Unified Medical Language System (UMLS). We propose a general, novel method for exploiting such resources via weight sharing. Prior work on weight sharing in neural networks has considered it largely as a means of model compression. In contrast, we treat weight sharing as a flexible mechanism for incorporating prior knowledge into neural models. We show that this approach consistently yields improved performance on classification tasks compared to baseline strategies that do not exploit weight sharing.