"Covid vaccine is against Covid but Oxford vaccine is made at Oxford!" Semantic Interpretation of Proper Noun Compounds

TL;DR

This paper introduces a large dataset and neural models for interpreting proper noun compounds like 'Covid vaccine', improving semantic understanding and integration with information extraction systems.

Contribution

It provides the first large-scale annotated dataset for proper noun compound interpretation and explores neural approaches with knowledge integration for better semantic understanding.

Findings

Adding knowledge improves interpretation accuracy by up to 2.8%.

Integrating models with Open IE increases extraction yield by 7.5%.

ProNCI dataset is 60 times larger than previous resources.

Abstract

Proper noun compounds, e.g., "Covid vaccine", convey information in a succinct manner (a "Covid vaccine" is a "vaccine that immunizes against the Covid disease"). These are commonly used in short-form domains, such as news headlines, but are largely ignored in information-seeking applications. To address this limitation, we release a new manually annotated dataset, ProNCI, consisting of 22.5K proper noun compounds along with their free-form semantic interpretations. ProNCI is 60 times larger than prior noun compound datasets and also includes non-compositional examples, which have not been previously explored. We experiment with various neural models for automatically generating the semantic interpretations from proper noun compounds, ranging from few-shot prompting to supervised learning, with varying degrees of knowledge about the constituent nouns. We find that adding targeted knowledge, particularly about the common noun, results in performance gains of upto 2.8%. Finally, we integrate our model generated interpretations with an existing Open IE system and observe an 7.5% increase in yield at a precision of 85%. The dataset and code are available at https://github.com/dair-iitd/pronci.