A BERT-based model with position-aware history answer embeddings and a learned history attention mechanism improves QuAC F1 by about one point over strong baselines, but multi-task learning with dialog acts does not help answer span prediction.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attentive History Selection for Conversational Question Answering
A BERT-based model with position-aware history answer embeddings and a learned history attention mechanism improves QuAC F1 by about one point over strong baselines, but multi-task learning with dialog acts does not help answer span prediction.