Specialising Paragraph Vectors for Text Polarity Detection

Fabio Tamburini


Abstract
This paper presents some experiments for specialising Paragraph Vectors, a new technique for creating text fragment (phrase, sentence, paragraph, text, ...) embedding vectors, for text polarity detection. The first extension regards the injection of polarity information extracted from a polarity lexicon into embeddings and the second extension aimed at inserting word order information into Paragraph Vectors. These two extensions, when training a logistic-regression classifier on the combined embeddings, were able to produce a relevant gain in performance when compared to the standard Paragraph Vector methods proposed by Le and Mikolov (2014).
Anthology ID:
L16-1189
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
1190–1195
Language:
URL:
https://aclanthology.org/L16-1189
DOI:
Bibkey:
Cite (ACL):
Fabio Tamburini. 2016. Specialising Paragraph Vectors for Text Polarity Detection. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1190–1195, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Specialising Paragraph Vectors for Text Polarity Detection (Tamburini, LREC 2016)
Copy Citation:
PDF:
https://aclanthology.org/L16-1189.pdf
Data
IMDb Movie Reviews