A discriminative alignment module, trained on 1.7K to 4.9K labeled sentence pairs and plugged into a Transformer MT model, outperforms FastAlign and attention baselines by 11 to 27 F1 points and improves projected NER.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Discriminative Neural Model for Cross-Lingual Word Alignment
A discriminative alignment module, trained on 1.7K to 4.9K labeled sentence pairs and plugged into a Transformer MT model, outperforms FastAlign and attention baselines by 11 to 27 F1 points and improves projected NER.