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

Keshav Kolluru, Gabriel Stanovsky, Mausam

Research output: Contribution to conferencePaperpeer-review

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.

Original languageAmerican English
Pages10407-10420
Number of pages14
StatePublished - 2022
Event2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Abu Dhabi, United Arab Emirates
Duration: 7 Dec 202211 Dec 2022

Conference

Conference2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period7/12/2211/12/22

Bibliographical note

Funding Information:
Keshav is supported by a TCS Fellowship. Mausam is supported by grants from Huawei, Google, Verisk, and a Jai Gupta Chair Fellowship. We thank KnowDis team for their help in data annotations and HPC, IIT Delhi for the computational resources. This work was supported in part by a research grant no. 2088 from the Israeli Ministry of Science and Technology.

Publisher Copyright:
© 2022 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of '“Covid vaccine is against Covid but Oxford vaccine is made at Oxford!” Semantic Interpretation of Proper Noun Compounds'. Together they form a unique fingerprint.

Cite this