Institutsseminar/2021-07-09: Unterschied zwischen den Versionen
Keine Bearbeitungszusammenfassung |
Keine Bearbeitungszusammenfassung |
||
Zeile 1: | Zeile 1: | ||
{{Termin | {{Termin | ||
|datum=2021/07/09 14:00:00 | |datum=2021/07/09 14:00:00 | ||
| | |online=https://sdqweb.ipd.kit.edu/wiki/Institutsseminar/Microsoft_Teams | ||
}} | }} |
Aktuelle Version vom 14. Januar 2022, 13:15 Uhr
Datum | Freitag, 9. Juli 2021 | |
---|---|---|
Uhrzeit | 14:00 – 14:30 Uhr (Dauer: 30 min) | |
Ort | ||
Webkonferenz | https://sdqweb.ipd.kit.edu/wiki/Institutsseminar/Microsoft Teams | |
Vorheriger Termin | Fr 2. Juli 2021 | |
Nächster Termin | Fr 16. Juli 2021 |
Termin in Kalender importieren: iCal (Download)
Vorträge
Vortragende(r) | Dennis Grötzinger |
---|---|
Titel | Exploring The Robustness Of The Natural Language Inference Capabilties Of T5 |
Vortragstyp | Bachelorarbeit |
Betreuer(in) | Jan Keim |
Vortragssprache | |
Vortragsmodus | |
Kurzfassung | Large language models like T5 perform excellently on various NLI benchmarks. However, it has been shown that even small changes in the structure of these tasks can significantly reduce accuracy. I build upon this insight and explore how robust the NLI skills of T5 are in three scenarios. First, I show that T5 is robust to some variations in the MNLI pattern, while others degenerate performance significantly. Second, I observe that some other patterns that T5 was trained on can be substituted for the MNLI pattern and still achieve good results. Third, I demonstrate that the MNLI pattern translate well to other NLI datasets, even improving accuracy by 13% in the case of RTE. All things considered, I conclude that the robustness of the NLI skills of T5 really depend on which alterations are applied. |
- Neuen Vortrag erstellen