Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations

TL;DR

This paper introduces a neural model that improves the interpretation of implicit noun-compound relations by representing paraphrases in a continuous space, enhancing generalization to unseen compounds and rare paraphrases.

Contribution

The proposed neural model advances noun-compound relation interpretation by enabling better generalization through continuous space representations, outperforming previous methods.

Findings

Improved performance on noun-compound paraphrasing.

Enhanced classification accuracy for implicit relations.

Better handling of unseen and rare noun-compounds.

Abstract

Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.