Daniel Marcu

5 paper cards in Mova's library · 2001–2006

Daniel Marcu wrote 5 of the papers Mova reads, in 2001–2006, most of them on Machine translation, Discourse analysis; often with Kevin Knight, Michel Galley, Bo Pang.

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

Ideas Mova took (1)

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

tried — Join only where the parents agree. When tools/translate merges two meta tokens from two translations of a verse into one concept (meta.rs), allow the join only if the heads they hang from already joined, and go top-down, stopping at the first disagreement.… (Syntax-based Alignment of Multiple Translations: Extracting… · translate r6-lattice (with barzilay-2003 I1): backbone by LCS of concepts across the four renderings; worse on dev, not kept)

Scalable Inference and Training of Context-Rich Syntactic Translation Models (2006)
The paper extends the rule extraction of Galley et al. (2004). Instead of keeping one minimal derivation per sentence pair, it builds a forest of many derivations, so that larger rules with more syntactic context and alternative readings of unaligned words are all available. It puts probabilities on these multi-level…
What's in a translation rule? (2004)
The paper gives a formal meaning to word alignments between a parsed English sentence and its translation.
Sentence Level Discourse Parsing using Syntactic and Lexical Information (2003)
The paper builds sentence-level RST discourse trees in two steps. First a probabilistic segmenter finds elementary discourse units inside a sentence, using syntactic and lexical features. Then a probabilistic parser builds the tree, using "dominance sets" taken from the Penn Treebank parse. The data are 385 WSJ…
Syntax-based Alignment of Multiple Translations: Extracting Paraphrases and Generating New Sentences (2003)
The authors take groups of 11 English translations of the same Chinese sentence (899 groups) and parse each one.
Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory (2001)
The paper describes how the RST Discourse Treebank was built: 385 American English articles from the Penn Treebank, each annotated with a rhetorical structure tree in Rhetorical Structure Theory.