When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases

Julie Weeds, Thomas Kober, Jeremy Reffin, David Weir


Abstract
Non-compositional phrases such as red herring and weakly compositional phrases such as spelling bee are an integral part of natural language (Sag, 2002). They are also the phrases that are difficult, or even impossible, for good compositional distributional models of semantics. Compositionality detection therefore provides a good testbed for compositional methods. We compare an integrated compositional distributional approach, using sparse high dimensional representations, with the ad-hoc compositional approach of applying simple composition operations to state-of-the-art neural embeddings.
Anthology ID:
E17-2085
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
529–534
Language:
URL:
https://aclanthology.org/E17-2085
DOI:
Bibkey:
Cite (ACL):
Julie Weeds, Thomas Kober, Jeremy Reffin, and David Weir. 2017. When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 529–534, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases (Weeds et al., EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/E17-2085.pdf