An Empirical Investigation of Beam-Aware Training in Supertagging

EMNLP, pp. 4534-4542, 2020.

Cited by: 0|Views25
EI

Abstract:

Structured prediction is often approached by training a locally normalized model with maximum likelihood and decoding approximately with beam search. This approach leads to mismatches as, during training, the model is not exposed to its mistakes and does not use beam search. Beam-aware training aims to address these problems, but unfort...More

Code:

Data:

Your rating :
0

 

Tags
Comments