Unsupervised Paraphrasability Prediction for Compound Nominalizations

John S. Y. Lee; Ho Hung Lim; Carol Webster

doi:10.18653/v1/2022.naacl-main.237

Unsupervised Paraphrasability Prediction for Compound Nominalizations

John S. Y. Lee, Ho Hung Lim, Carol Webster

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

75 Downloads (CityUHK Scholars)

Abstract

Commonly found in academic and formal texts, a nominalization uses a deverbal noun to describe an event associated with its corresponding verb. Nominalizations can be difficult to interpret because of ambiguous semantic relations between the deverbal noun and its arguments. Automatic generation of clausal paraphrases for nominalizations can help disambiguate their meaning. However, previous work has not identified cases where it is awkward or impossible to paraphrase a compound nominalization. This paper investigates unsupervised prediction of paraphrasability, which determines whether the prenominal modifier of a nominalization can be re-written as a noun or adverb in a clausal paraphrase. We adopt the approach of overgenerating candidate paraphrases followed by candidate ranking with a neural language model. In experiments on an English dataset, we show that features from an Abstract Meaning Representation graph lead to statistically significant improvement in both paraphrasability prediction and paraphrase generation.

Original language	English
Title of host publication	The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Subtitle of host publication	Proceedings of the Conference
Publisher	Association for Computational Linguistics
Pages	3254-3263
ISBN (Print)	9781955917711
DOIs	https://doi.org/10.18653/v1/2022.naacl-main.237
Publication status	Published - Jul 2022
Event	2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022) - Virtual, Seattle, United States Duration: 10 Jul 2022 → 15 Jul 2022 https://2022.naacl.org/program/

Publication series

Name	NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference	2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)
Country/Territory	United States
City	Seattle
Period	10/07/22 → 15/07/22
Internet address	https://2022.naacl.org/program/

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.18653/v1/2022.naacl-main.237

1109541822.pdfFinal Published version, 216 KBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Lee, J. S. Y., Lim, H. H., & Webster, C. (2022). Unsupervised Paraphrasability Prediction for Compound Nominalizations. In The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Conference (pp. 3254-3263). (NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.naacl-main.237

Lee, John S. Y. ; Lim, Ho Hung ; Webster, Carol. / Unsupervised Paraphrasability Prediction for Compound Nominalizations. The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Conference . Association for Computational Linguistics, 2022. pp. 3254-3263 (NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

@inproceedings{350a2e6def04409db2292c6b4d9e5e26,

title = "Unsupervised Paraphrasability Prediction for Compound Nominalizations",

abstract = "Commonly found in academic and formal texts, a nominalization uses a deverbal noun to describe an event associated with its corresponding verb. Nominalizations can be difficult to interpret because of ambiguous semantic relations between the deverbal noun and its arguments. Automatic generation of clausal paraphrases for nominalizations can help disambiguate their meaning. However, previous work has not identified cases where it is awkward or impossible to paraphrase a compound nominalization. This paper investigates unsupervised prediction of paraphrasability, which determines whether the prenominal modifier of a nominalization can be re-written as a noun or adverb in a clausal paraphrase. We adopt the approach of overgenerating candidate paraphrases followed by candidate ranking with a neural language model. In experiments on an English dataset, we show that features from an Abstract Meaning Representation graph lead to statistically significant improvement in both paraphrasability prediction and paraphrase generation.",

author = "Lee, {John S. Y.} and Lim, {Ho Hung} and Carol Webster",

year = "2022",

month = jul,

doi = "10.18653/v1/2022.naacl-main.237",

language = "English",

isbn = "9781955917711",

series = "NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",

publisher = "Association for Computational Linguistics",

pages = "3254--3263",

booktitle = "The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",

address = "United States",

note = "2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022) ; Conference date: 10-07-2022 Through 15-07-2022",

url = "https://2022.naacl.org/program/",

}

Lee, JSY, Lim, HH & Webster, C 2022, Unsupervised Paraphrasability Prediction for Compound Nominalizations. in The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Conference . NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, Association for Computational Linguistics, pp. 3254-3263, 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022), Seattle, United States, 10/07/22. https://doi.org/10.18653/v1/2022.naacl-main.237

Unsupervised Paraphrasability Prediction for Compound Nominalizations. / Lee, John S. Y.; Lim, Ho Hung; Webster, Carol.
The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Conference . Association for Computational Linguistics, 2022. p. 3254-3263 (NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Unsupervised Paraphrasability Prediction for Compound Nominalizations

AU - Lee, John S. Y.

AU - Lim, Ho Hung

AU - Webster, Carol

PY - 2022/7

Y1 - 2022/7

N2 - Commonly found in academic and formal texts, a nominalization uses a deverbal noun to describe an event associated with its corresponding verb. Nominalizations can be difficult to interpret because of ambiguous semantic relations between the deverbal noun and its arguments. Automatic generation of clausal paraphrases for nominalizations can help disambiguate their meaning. However, previous work has not identified cases where it is awkward or impossible to paraphrase a compound nominalization. This paper investigates unsupervised prediction of paraphrasability, which determines whether the prenominal modifier of a nominalization can be re-written as a noun or adverb in a clausal paraphrase. We adopt the approach of overgenerating candidate paraphrases followed by candidate ranking with a neural language model. In experiments on an English dataset, we show that features from an Abstract Meaning Representation graph lead to statistically significant improvement in both paraphrasability prediction and paraphrase generation.

AB - Commonly found in academic and formal texts, a nominalization uses a deverbal noun to describe an event associated with its corresponding verb. Nominalizations can be difficult to interpret because of ambiguous semantic relations between the deverbal noun and its arguments. Automatic generation of clausal paraphrases for nominalizations can help disambiguate their meaning. However, previous work has not identified cases where it is awkward or impossible to paraphrase a compound nominalization. This paper investigates unsupervised prediction of paraphrasability, which determines whether the prenominal modifier of a nominalization can be re-written as a noun or adverb in a clausal paraphrase. We adopt the approach of overgenerating candidate paraphrases followed by candidate ranking with a neural language model. In experiments on an English dataset, we show that features from an Abstract Meaning Representation graph lead to statistically significant improvement in both paraphrasability prediction and paraphrase generation.

UR - http://www.scopus.com/inward/record.url?scp=85138343419&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85138343419&origin=recordpage

U2 - 10.18653/v1/2022.naacl-main.237

DO - 10.18653/v1/2022.naacl-main.237

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781955917711

T3 - NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

SP - 3254

EP - 3263

BT - The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics

T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)

Y2 - 10 July 2022 through 15 July 2022

ER -

Lee JSY, Lim HH, Webster C. Unsupervised Paraphrasability Prediction for Compound Nominalizations. In The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Conference . Association for Computational Linguistics. 2022. p. 3254-3263. (NAACL - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). doi: 10.18653/v1/2022.naacl-main.237

Unsupervised Paraphrasability Prediction for Compound Nominalizations

Abstract

Publication series

Conference

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this