Chris Quirk

3 paper cards in Mova's library · 2004–2008

Chris Quirk wrote 3 of the papers Mova reads, in 2004–2008, most of them on Machine translation; often with Arul Menezes, Chris Brockett, Colin Cherry.

The profile is the library's match of the name; two people with one name are not always told apart.

Ideas Mova took (2)

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

tried — Structural insertion templates by POS. Learn from verse pairs rules such as NOUN NOUN to NOUN of NOUN, keyed by enum tags, and use them in the encoder when the concept is unseen. This gives the encoder a fallback below the concept-level contexts. Measure the… (Syntactic Models for Structural Word Insertion and Deletion… · translate fwt.rs: per author pair insert/drop table of function words on the meta-world (r5-fwt); kjv→web 249.6→248.6 dev, shuffled-table control red; kept…)
tried — Deletion only where it helps. Keep structural deletion off as a standard rule and allow it through the author DELTA, which the paper's direction finding suggests. Compare the standard with and without deletion per author pair, using the rule that a delta… (Syntactic Models for Structural Word Insertion and Deletion… · translate fwt.rs: deletion only where it holds ≥3 cases and half the context's (r5-fwt), kept)

Syntactic Models for Structural Word Insertion and Deletion during Translation (2008)
The treelet translation system uses unlexicalised order templates for reordering, separate from lexical treelets.
Dependency Treelet Translation: Syntactically Informed Phrasal SMT (2005)
The system takes a source sentence, parses it into a dependency tree, and projects that tree onto the target sentence through the word alignment.
Monolingual Machine Translation for Paraphrase Generation (2004)
The paper treats paraphrase generation as translation within one language. Training pairs are sentences from news stories that different web sources wrote about the same event, clustered and aligned at sentence level. Word alignment uses the GIZA++ IBM models and an HMM, with alignment error rate 11.58% on 250…