Learning syntactic structure

27 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, background): “The features use ngrams defined over text or common cover link (CCL) (Seginer, 2007) structures as the basic units of information over which similarity calculations are performed.”
Referential Translation Machines for Predicting Translation Quality (2014, methodology): “Table 1 depicts the parsing output obtained by CCL for the following sentence from WSJ23 3: Many fund managers argue that now ’s the time to buy .”
Referential translation machines for predicting semantic similarity (2015, methodology): “Features include correlation, recall, F 1 over both, v 2 , j v 2 j , ZWV over them (except recall), and vector length for each n - gram or CCLs for S and T ({24 (cid:5) (3 ?”
Findings of the 2013 Workshop on Statistical Machine Translation (2013, methodology): “The sentence-level features are described in MTPP (Bic¸ici et al., 2013); they include monolingual or bilingual features using n-grams deﬁned over text or common cover link (CCL) (Seginer, 2007) (Specia, 2011).”
Referential Translation Machines for Quality Estimation (2013, methodology): “In broad categories, these word-level features are: • CCL: Uses CCL links.”