Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation

TL;DR

This paper investigates how transfer and multi-task learning techniques can improve neural models' ability to interpret noun-noun compounds, especially for rare relations, through extensive experiments and error analysis.

Contribution

It demonstrates that transfer learning and multi-task learning significantly enhance the generalization and accuracy of neural classifiers for semantic interpretation of noun-noun compounds.

Findings

Transfer learning improves relation classification accuracy.

Multi-task learning boosts F1 scores on difficult relations.

Dual annotation enhances overall model performance.

Abstract

In this paper, we empirically evaluate the utility of transfer and multi-task learning on a challenging semantic classification task: semantic interpretation of noun--noun compounds. Through a comprehensive series of experiments and in-depth error analysis, we show that transfer learning via parameter initialization and multi-task learning via parameter sharing can help a neural classification model generalize over a highly skewed distribution of relations. Further, we demonstrate how dual annotation with two distinct sets of relations over the same set of compounds can be exploited to improve the overall accuracy of a neural classifier and its F1 scores on the less frequent, but more difficult relations.