Abstrakti
Task 5 of SemEval-2017 involves fine-grained sentiment analysis on financial
microblogs and news. Our solution for determining the sentiment score extends
an earlier convolutional neural network for sentiment analysis in several ways.
We explicitly encode a focus on a particular company, we apply a data
augmentation scheme, and use a larger data collection to complement the small
training data provided by the task organizers. The best results were achieved
by training a model on an external dataset and then tuning it using the
provided training dataset.
microblogs and news. Our solution for determining the sentiment score extends
an earlier convolutional neural network for sentiment analysis in several ways.
We explicitly encode a focus on a particular company, we apply a data
augmentation scheme, and use a larger data collection to complement the small
training data provided by the task organizers. The best results were achieved
by training a model on an external dataset and then tuning it using the
provided training dataset.
Alkuperäiskieli | englanti |
---|---|
Otsikko | 11th International Workshop on Semantic Evaluations (SemEval-2017) : Proceedings of the Workshop |
Sivumäärä | 5 |
Julkaisupaikka | Stroudsburg, PA |
Kustantaja | The Association for Computational Linguistics |
Julkaisupäivä | elok. 2017 |
Sivut | 842-846 |
ISBN (elektroninen) | 978-1-945626-55-5 |
DOI - pysyväislinkit | |
Tila | Julkaistu - elok. 2017 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisuussa |
Tapahtuma | International Workshop on Semantic Evaluations - New Orleans, Yhdysvallat (USA) Kesto: 5 kesäk. 2018 → 6 kesäk. 2018 Konferenssinumero: 12 http://alt.qcri.org/semeval2018/ |
Tieteenalat
- 113 Tietojenkäsittely- ja informaatiotieteet
Projektit
-
LLL: Language Learning Lab
Yangarber, R. (Projektinjohtaja), Katinskaia, A. (Osallistuja), Hou, J. (Osallistuja), Furlan, G. (Osallistuja) & Kylliäinen, I. P. (Osallistuja)
Projekti: Tutkimusprojekti