Representation Learning by Nada Lavrač & Vid Podpečan & Marko Robnik-Šikonja

Representation Learning by Nada Lavrač & Vid Podpečan & Marko Robnik-Šikonja

Author:Nada Lavrač & Vid Podpečan & Marko Robnik-Šikonja
Language: eng
Format: epub
ISBN: 9783030688172
Publisher: Springer International Publishing


Conversational input-response task

assures inclusion of parsed conversational data (Henderson et al. 2017), which uses pairs of email messages and their responses as the prediction task.

Classification task

for training on supervised data.

The sentence encoding demonstrated a strong performance on several NLP tasks (sentiment classification, subjectivity of sentences, question classification, semantic textual similarity) and has beaten other sentence representations on hate speech classification (Miok et al. 2019).



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.