Papers by Johann Petrak
A Deep Neural Network Sentence Level Classification Method with Context Information (D18-1)
Copied to clipboard
| Challenge: | Existing methods that use context for sentence classification are difficult to scale . Usually, sentences are treated as separate instances for the task . however, in many situations the sentence that is the focus of classification appears in a context that can provide additional information. |
| Approach: | They propose a method that uses potentially large contexts to classify sentences . they use an LSTM, and short-span features to classize sentences based on a stacked CNN . |
| Outcome: | The proposed method consistently improves on two different datasets. |
GERMS-AT: A Sexism/Misogyny Dataset of Forum Comments from an Austrian Online Newspaper (2024.lrec-main)
Copied to clipboard
| Challenge: | sexism/misogyny dataset extracted from comments of online forum of newspaper . corpus of 8 000 comments annotated with 5 levels of sexist/mistoginist . |
| Approach: | They present a sexism/misogyny dataset extracted from comments of an online forum of an Austrian newspaper. |
| Outcome: | The results show that the corpus of comments is sexist/misogynistic and has 5 levels of sexism/mistoginess. |