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

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Non-compositional phrases such as red herring and weakly compositional phrases such as spelling bee are an integral part of
natural language (Sag et al., 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 adhoc
compositional approach of applying simple composition operations to state-ofthe-art neural embeddings.

Original language	English
Title of host publication	Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers
Publisher	Association for Computational Linguistics
Pages	529-534
Number of pages	6
Publication status	Published - 7 Apr 2017
Event	The 15th Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017

Conference

Conference	The 15th Conference of the European Chapter of the Association for Computational Linguistics
Abbreviated title	EACL 2017
Country/Territory	Spain
City	Valencia
Period	3/04/17 → 7/04/17

Access to Document

https://www.aclweb.org/anthology/E17-2085/Licence: Creative Commons: Attribution (CC-BY)

Cite this

Weeds, J., Kober, T., Reffin, J., & Weir, D. (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, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers (pp. 529-534). Association for Computational Linguistics. https://www.aclweb.org/anthology/E17-2085/

Weeds, Julie ; Kober, Thomas ; Reffin, Jeremy et al. / When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers. Association for Computational Linguistics, 2017. pp. 529-534

@inproceedings{6815dcb2c4674099a5b02c878659b96c,

title = "When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases",

abstract = "Non-compositional phrases such as red herring and weakly compositional phrases such as spelling bee are an integral part of natural language (Sag et al., 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 adhoc compositional approach of applying simple composition operations to state-ofthe-art neural embeddings.",

author = "Julie Weeds and Thomas Kober and Jeremy Reffin and David Weir",

year = "2017",

month = apr,

day = "7",

language = "English",

pages = "529--534",

booktitle = "Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers",

publisher = "Association for Computational Linguistics",

note = "The 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 ; Conference date: 03-04-2017 Through 07-04-2017",

}

Weeds, J, Kober, T, Reffin, J & Weir, D 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, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers. Association for Computational Linguistics, pp. 529-534, The 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 3/04/17. <https://www.aclweb.org/anthology/E17-2085/>

When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases. / Weeds, Julie; Kober, Thomas; Reffin, Jeremy et al.
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers. Association for Computational Linguistics, 2017. p. 529-534.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - When a Red Herring in Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases

AU - Weeds, Julie

AU - Kober, Thomas

AU - Reffin, Jeremy

AU - Weir, David

PY - 2017/4/7

Y1 - 2017/4/7

N2 - Non-compositional phrases such as red herring and weakly compositional phrases such as spelling bee are an integral part of natural language (Sag et al., 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 adhoc compositional approach of applying simple composition operations to state-ofthe-art neural embeddings.

AB - Non-compositional phrases such as red herring and weakly compositional phrases such as spelling bee are an integral part of natural language (Sag et al., 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 adhoc compositional approach of applying simple composition operations to state-ofthe-art neural embeddings.

M3 - Conference contribution

SP - 529

EP - 534

BT - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers

PB - Association for Computational Linguistics

T2 - The 15th Conference of the European Chapter of the Association for Computational Linguistics

Y2 - 3 April 2017 through 7 April 2017

ER -

Weeds J, Kober T, Reffin J, Weir D. 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, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers. Association for Computational Linguistics. 2017. p. 529-534

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

Abstract

Conference

Access to Document

Fingerprint

Cite this