Matches in SemOpenAlex for { <https://semopenalex.org/work/W213376400> ?p ?o ?g. }
- W213376400 abstract "The task of automatic machine translation (MT) is the focus of a huge variety of active research efforts, both because of the intrinsic utility of this difficult task, and the theoretical and linguistic insights that arise from modeling relationships between natural languages. However, MT systems that leverage syntactic information are only recently becoming practical, and in a typical system of this sort, syntactic information is generated by monolingual parsers; the task of explicitly modeling syntactic relationships between target and source languages is yet to be fully explored. This thesis investigates the problem of finding syntactic parse trees of target and/or source sentences that are more appropriate for use in a syntactic MT system. Two basic methodologies are explored. First, we present a sequence of two statistical models that leverage bilingual information to improve the linguistic quality of syntactic parses, as measured by their ability to replicate human-generated gold-standard annotations. The first model uses word to word alignments as an external source of information, while the second models the alignments jointly. These models are both quite effective at improving the intrinsic quality of the parse trees, and the second model additionally improves word alignment performance. However, while the two models achieve similar parsing improvements, we find that improving parses in conjunction with word alignments is much more helpful for the downstream machine translation task. In the next part of the thesis, we explore this finding further by investigating the effects on MT performance of agreement between parse trees and word alignments. We present a simple method for transforming input trees in a way that ignores gold-standard annotations, concentrating instead on improving syntactic agreement directly. In experiments, we find that though we obviously lose fidelity to more linguistically informed treebank annotation guidelines, this transformation-based approach yields the strongest improvements in syntactic machine translation." @default.
- W213376400 created "2016-06-24" @default.
- W213376400 creator A5003197445 @default.
- W213376400 creator A5004921249 @default.
- W213376400 date "2012-01-01" @default.
- W213376400 modified "2023-09-26" @default.
- W213376400 title "Syntactic agreement in bilingual corpora" @default.
- W213376400 cites W108437174 @default.
- W213376400 cites W1510052640 @default.
- W213376400 cites W1551202288 @default.
- W213376400 cites W1598771940 @default.
- W213376400 cites W1623072288 @default.
- W213376400 cites W1632114991 @default.
- W213376400 cites W17659133 @default.
- W213376400 cites W1979495315 @default.
- W213376400 cites W1999993003 @default.
- W213376400 cites W2000566875 @default.
- W213376400 cites W2006912660 @default.
- W213376400 cites W2006969979 @default.
- W213376400 cites W2031196180 @default.
- W213376400 cites W2036453285 @default.
- W213376400 cites W2061910127 @default.
- W213376400 cites W2081687495 @default.
- W213376400 cites W2092654472 @default.
- W213376400 cites W2096204319 @default.
- W213376400 cites W2096894677 @default.
- W213376400 cites W2100281225 @default.
- W213376400 cites W2101105183 @default.
- W213376400 cites W2101656755 @default.
- W213376400 cites W2102366626 @default.
- W213376400 cites W2103156738 @default.
- W213376400 cites W2104163628 @default.
- W213376400 cites W2105891181 @default.
- W213376400 cites W2107705235 @default.
- W213376400 cites W2108740414 @default.
- W213376400 cites W2109389484 @default.
- W213376400 cites W2111142112 @default.
- W213376400 cites W2115526192 @default.
- W213376400 cites W2116316001 @default.
- W213376400 cites W2116957398 @default.
- W213376400 cites W2117400858 @default.
- W213376400 cites W2119224513 @default.
- W213376400 cites W2119314391 @default.
- W213376400 cites W2120340025 @default.
- W213376400 cites W2124807415 @default.
- W213376400 cites W2125712079 @default.
- W213376400 cites W2126270798 @default.
- W213376400 cites W2128972636 @default.
- W213376400 cites W2133229022 @default.
- W213376400 cites W2134729743 @default.
- W213376400 cites W2138165032 @default.
- W213376400 cites W2140343992 @default.
- W213376400 cites W2143008661 @default.
- W213376400 cites W2143954309 @default.
- W213376400 cites W2144600658 @default.
- W213376400 cites W2146574666 @default.
- W213376400 cites W2152213375 @default.
- W213376400 cites W2152561660 @default.
- W213376400 cites W2152937686 @default.
- W213376400 cites W2153653739 @default.
- W213376400 cites W2153800732 @default.
- W213376400 cites W2158388102 @default.
- W213376400 cites W2161792612 @default.
- W213376400 cites W2164454850 @default.
- W213376400 cites W2166905217 @default.
- W213376400 cites W2168596725 @default.
- W213376400 cites W2169724380 @default.
- W213376400 cites W2170927607 @default.
- W213376400 cites W2413580944 @default.
- W213376400 cites W2437005631 @default.
- W213376400 cites W2963814856 @default.
- W213376400 cites W3029645440 @default.
- W213376400 cites W33032091 @default.
- W213376400 cites W55636956 @default.
- W213376400 cites W82889912 @default.
- W213376400 cites W89239156 @default.
- W213376400 cites W1930029350 @default.
- W213376400 hasPublicationYear "2012" @default.
- W213376400 type Work @default.
- W213376400 sameAs 213376400 @default.
- W213376400 citedByCount "0" @default.
- W213376400 crossrefType "journal-article" @default.
- W213376400 hasAuthorship W213376400A5003197445 @default.
- W213376400 hasAuthorship W213376400A5004921249 @default.
- W213376400 hasConcept C120665830 @default.
- W213376400 hasConcept C121332964 @default.
- W213376400 hasConcept C138885662 @default.
- W213376400 hasConcept C153083717 @default.
- W213376400 hasConcept C154945302 @default.
- W213376400 hasConcept C162324750 @default.
- W213376400 hasConcept C186644900 @default.
- W213376400 hasConcept C187736073 @default.
- W213376400 hasConcept C192209626 @default.
- W213376400 hasConcept C203005215 @default.
- W213376400 hasConcept C204321447 @default.
- W213376400 hasConcept C2780451532 @default.
- W213376400 hasConcept C2781466058 @default.
- W213376400 hasConcept C41008148 @default.
- W213376400 hasConcept C41895202 @default.
- W213376400 hasConcept C90805587 @default.