[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/daniel-marcu/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Daniel Marcu # 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](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/), [Discourse analysis](https://md.mova.elamur.ai/free/en/docs/papers/topics/discourse-analysis/); often with [Kevin Knight](https://md.mova.elamur.ai/free/en/docs/papers/authors/kevin-knight/), [Michel Galley](https://md.mova.elamur.ai/free/en/docs/papers/authors/michel-galley/), Bo Pang. [OpenAlex](https://openalex.org/A5005020376) · [**h-index 58**](https://openalex.org/authors/A5005020376) · [17433 citations](https://openalex.org/authors/A5005020376) · [209 works](https://openalex.org/works?filter=author.id:A5005020376) — openalex, 2026-10-18 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Daniel+Marcu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Daniel+Marcu) · [dblp](https://dblp.org/search?q=Daniel+Marcu) · [ACL Anthology](https://aclanthology.org/search/?q=Daniel+Marcu) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Daniel+Marcu) Topics: [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/) 3 · [Discourse analysis](https://md.mova.elamur.ai/free/en/docs/papers/topics/discourse-analysis/) 2 ## 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…](https://md.mova.elamur.ai/free/en/docs/papers/pang-2003-syntax-based-alignment-multiple-translations/) · translate r6-lattice (with barzilay-2003 I1): backbone by LCS of concepts across the four renderings; worse on dev, not kept)* ## Papers 1. **[Scalable Inference and Training of Context-Rich Syntactic Translation Models](https://md.mova.elamur.ai/free/en/docs/papers/galley-2006-scalable-inference-training-context-rich/)** *(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… 2. **[What's in a translation rule?](https://md.mova.elamur.ai/free/en/docs/papers/galley-2004-what-s-translation-rule/)** *(2004)* The paper gives a formal meaning to word alignments between a parsed English sentence and its translation. 3. **[Sentence Level Discourse Parsing using Syntactic and Lexical Information](https://md.mova.elamur.ai/free/en/docs/papers/soricut-2003-sentence-level-discourse-parsing-syntactic/)** *(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… 4. **[Syntax-based Alignment of Multiple Translations: Extracting Paraphrases and Generating New Sentences](https://md.mova.elamur.ai/free/en/docs/papers/pang-2003-syntax-based-alignment-multiple-translations/)** *(2003)* The authors take groups of 11 English translations of the same Chinese sentence (899 groups) and parse each one. 5. **[Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory](https://md.mova.elamur.ai/free/en/docs/papers/carlson-2001-building-discourse-tagged-corpus-framework/)** *(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. ## Co-authors (11) - [Kevin Knight](https://md.mova.elamur.ai/free/en/docs/papers/authors/kevin-knight/) ×3 - [Michel Galley](https://md.mova.elamur.ai/free/en/docs/papers/authors/michel-galley/) ×2 - Bo Pang - Ignacio Thayer - [Jonathan Graehl](https://md.mova.elamur.ai/free/en/docs/papers/authors/jonathan-graehl/) - [Lynn Carlson](https://md.mova.elamur.ai/free/en/docs/papers/authors/lynn-carlson/) - [Mark Hopkins](https://md.mova.elamur.ai/free/en/docs/papers/authors/mark-hopkins/) - Mary Ellen Okurovsky - Radu Soricut - Steve DeNeefe - Wei Wang - [← previous Daniel Khashabi](https://md.mova.elamur.ai/free/en/docs/papers/authors/daniel-khashabi/) - [next → Daniel Zeman](https://md.mova.elamur.ai/free/en/docs/papers/authors/daniel-zeman/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)