Juan Antonio Pérez-Ortiz

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

• tried — A count test for lexicon merges. Merge two concepts (or two meta tokens) only when their proportions over the same contexts agree under a dissimilarity like the paper's, computed from counts. This targets open problem 2. Measure the merges kept, including… (Learning synchronous context-free grammars with multiple… · translate r6-lb: a count/lower-bound test for merges (with riding-2008 I1); kept)

Papers

1. Learning synchronous context-free grammars with multiple specialised non-terminals for hierarchical phrase-based translation (2020)
   Hierarchical phrase-based translation uses one nonterminal, which the authors take to be overloaded. They give every gap of every extracted phrase pair its own nonterminal, which yields about 850,000 nonterminals on a small English-Spanish EMEA corpus (sentences up to 20 words). Two nonterminals are then merged when…
2. Integrating shallow-transfer rules into phrase-based statistical machine translation (2011)
   A hybrid method that feeds a phrase-based statistical system with the knowledge of a shallow-transfer rule system.

Co-authors (3)

• Felipe Sanchez-Martinez ×2
• Rafael C. Carrasco
• Víctor M. Sánchez-Cartagena

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/juan-antonio-perez-ortiz/