• Refine your search:
  • 
    Keyword:
    
    • Machine translation (5)
    • Word alignment (3)
    • Bayesian learning (1)
    • Bilingual lexicon induction (1)
    • Efficient decoding (1)
    • Empty category (1)
    • Factorization (1)
    • Latent annotation (1)
    • Machine learning (1)
    • Morphology (1)
    •   more
  • 
    Creator / Publisher:
    
    • Gildea, Daniel J. (5)
    • Chung, Tagyoung (1)
    • Eyigoz, Kadriye Elif (1)
    • Oflazer, Kemal (1)
    • Riley, Parker (1)
    • Zhang, Hao (1)
    • Zhao, Shaojun (1)
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Hits 1 – 5 of 5 1 Text rewriting with missing supervision Gildea, Daniel J.; Riley, Parker. - : University of Rochester, 2021 BASE Show details 2 Morphology modeling for statistical machine translation Eyigoz, Kadriye Elif (1977 - ); Gildea, Daniel J.; Oflazer, Kemal. - : University of Rochester, 2014 Abstract: Thesis (Ph. D.)--University of Rochester. Dept. of Computer Science, 2014. ; Word-alignment is the initial step in most state-of-the art approaches to statistical machine translation. Morphologically rich languages pose problems for current statistical machine translation systems, including word-alignment, the most common problem being data sparsity. Current word-alignment models do not take into account morphology beyond merely treating morphemes as words. We present a new word alignment model that distinguishes between words and morphemes. Our model does not collapse words and morphemes into one single category, therefore we can legitimately talk about words and their morphemes in line with the linguistic conception of these terms. We adopt a two-level representation of alignment: the first level involves word alignment, the second level involves morpheme alignment in the scope of a given word alignment. Two-level alignment models (TAM) can align rarely occurring words through their frequently occurring morphemes. Our model induces word and morpheme alignments jointly using the expectation maximization algorithm. We present the HMM extension of TAM, which is an instance of a multi-scale HMM. The two-level HMM we present addresses reordering between morpheme positions and word positions simultaneously. Keyword: Machine translation; Morphology; Statistical machine translation; Word alignment URL: http://hdl.handle.net/1802/28475 BASE Hide details 3 Using latent information for natural language processing tasks Chung, Tagyoung; Gildea, Daniel J.. - : University of Rochester, 2013 BASE Show details 4 On word alignment models for statistical machine translation Zhao, Shaojun; Gildea, Daniel J.. - : University of Rochester, 2011 BASE Show details 5 Handling complexity of synchronous grammars for machine translation Zhang, Hao (1978 - ); Gildea, Daniel J.. - : University of Rochester, 2008 BASE Show details

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 5 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0