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).
Specialising Paragraph Vectors for Text Polarity Detection / Tamburini, F.. - ELETTRONICO. - (2016), pp. 1190-1195. (Intervento presentato al convegno Language Resources and Evaluation Conference, 10th edition (LREC) tenutosi a Portorož, Slovenia nel 23-28 May 2016).
Specialising Paragraph Vectors for Text Polarity Detection
TAMBURINI, FABIO
2016
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).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.