Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks

14 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Findings of the 2014 Workshop on Statistical Machine Translation (2014, methodology): “3) are trained on black-box features extracted using Q U E ST in addition to features based on word alignments, word posterior probabilities and diversity scores (Souza et al., 2013).”
Findings of the 2013 Workshop on Statistical Machine Translation (2013, methodology): “…word alignments is used to extract quantitative (amount and distribution of the alignments) and qualitative (importance of the aligned terms) features under the assumption that alignment information can help tasks where sentence-level semantic relations need to be identiﬁed (Souza et al., 2013).”