Sentiment analysis is the process of classifying natural lan-guage sentences as expressing positive or negative sentiments, and it is a crucial task where the explanation of a prediction might arguably be as necessary as the prediction itself. We analysed di fierent explanation techniques, and we applied them to the classification task of Sentiment Analysis. We explored how attention-based techniques can be exploited to extract meaningful sentiment scores with a lower computational cost than existing XAI methods.
Explainability Methods for Natural Language Processing: Applications to Sentiment Analysis / Bodria F.; Panisson A.; Perotti A.; Piaggesi S.. - ELETTRONICO. - 2646:(2020), pp. 100-107. (Intervento presentato al convegno 28th Italian Symposium on Advanced Database Systems, SEBD 2020 tenutosi a Villasimius, Italy (virtual due to Covid-19 pandemic) nel June 21 - 24, 2020).
Explainability Methods for Natural Language Processing: Applications to Sentiment Analysis
Piaggesi S.
2020
Abstract
Sentiment analysis is the process of classifying natural lan-guage sentences as expressing positive or negative sentiments, and it is a crucial task where the explanation of a prediction might arguably be as necessary as the prediction itself. We analysed di fierent explanation techniques, and we applied them to the classification task of Sentiment Analysis. We explored how attention-based techniques can be exploited to extract meaningful sentiment scores with a lower computational cost than existing XAI methods.File | Dimensione | Formato | |
---|---|---|---|
18-paper.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione
626.14 kB
Formato
Adobe PDF
|
626.14 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.