Evaluation of Simple Distributional Compositional Operations on Longer Texts

Tamara Polajnar, Laura Rimell, Stephen Clark


Abstract
Distributional semantic models have been effective at representing linguistic semantics at the word level, and more recently research has moved on to the construction of distributional representations for larger segments of text. However, it is not well understood how the composition operators that work well on short phrase-based models scale up to full-length sentences. In this paper we test several simple compositional methods on a sentence-length similarity task and discover that their performance peaks at fewer than ten operations. We also introduce a novel sentence segmentation method that reduces the number of compositional operations.
Anthology ID:
L14-1076
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
4440–4443
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/110_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Tamara Polajnar, Laura Rimell, and Stephen Clark. 2014. Evaluation of Simple Distributional Compositional Operations on Longer Texts. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4440–4443, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
Evaluation of Simple Distributional Compositional Operations on Longer Texts (Polajnar et al., LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/110_Paper.pdf