Vortrag: Fast breaking and slow building of textual inference models
Wann
Montag, 16. Dezember 2019
10 bis 11:30 Uhr
Wo
G 209
Veranstaltet von
FB Linguistik/AG Butt
Vortragende Person/Vortragende Personen:
Vered Shwartz (Institute for Artificial Intelligence - AI2 and Paul G. Allen School of Computer Science & Engineering, University of Washington.)
With the availability of massive training data for the task, natural language inference (NLI) has become the go-to task for testing natural language understanding. But a recent line of work showed that the current benchmarks over-estimate the actual performance on the task, and that models often perform well even when shown incomplete data, due to overfitting to benchmark artifacts.