Learning to Predict Novel Noun-Noun Compounds

Prajit Dhar, Lonneke van der Plas


Abstract
We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus. We train compositional models on observed compounds, more specifically the composed distributed representations of their constituents across a time-stamped corpus, while giving it corrupted instances (where head or modifier are replaced by a random constituent) as negative evidence. The model captures generalisations over this data and learns what combinations give rise to plausible compounds and which ones do not. After training, we query the model for the plausibility of automatically generated novel combinations and verify whether the classifications are accurate. For our best model, we find that in around 85% of the cases, the novel compounds generated are attested in previously unseen data. An additional estimated 5% are plausible despite not being attested in the recent corpus, based on judgments from independent human raters.
Anthology ID:
W19-5105
Volume:
Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
Month:
August
Year:
2019
Address:
Florence, Italy
Venue:
MWE
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
30–39
Language:
URL:
https://aclanthology.org/W19-5105
DOI:
10.18653/v1/W19-5105
Bibkey:
Cite (ACL):
Prajit Dhar and Lonneke van der Plas. 2019. Learning to Predict Novel Noun-Noun Compounds. In Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), pages 30–39, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Learning to Predict Novel Noun-Noun Compounds (Dhar & van der Plas, MWE 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5105.pdf
Code
 prajitdhar/Compounding