| 1 |
Measuring the divergence of dependency structures cross-linguistically to improve syntactic projection algorithms
|
|
|
|
In: http://www.lrec-conf.org/proceedings/lrec2012/pdf/971_Paper.pdf (2012)
|
|
Abstract:
Syntactic parses can provide valuable information for many NLP tasks, such as machine translation, semantic analysis, etc. However, most of the world’s languages do not have large amounts of syntactically annotated corpora available for building parsers. Syntactic projection techniques attempt to address this issue by using parallel corpora between resource-poor and resource-rich languages, bootstrapping the resource-poor language with the syntactic analysis of the resource-rich language. In this paper, we investigate the possibility of using small, parallel, annotated corpora to automatically detect divergent structural patterns between two languages. These patterns can then be used to improve structural projection algorithms, allowing for better performing NLP tools for resource-poor languages, in particular those that may not have large amounts of annotated data necessary for traditional, fully-supervised methods. While this detection process is not exhaustive, we demonstrate that important instances of divergence are picked up with minimal prior knowledge of a given language pair.
|
|
Keyword:
Multilinguality; Syntactic Projection; Translation Divergence
|
|
URL: http://www.lrec-conf.org/proceedings/lrec2012/pdf/971_Paper.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.383.6054
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Language ID for a thousand languages
|
|
|
|
In: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/601.pdf (2010)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Language ID in the context of harvesting language data off the web
|
|
|
|
In: http://www.aclweb.org/anthology-new/E/E09/E09-1099.pdf (2009)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Automatically Identifying Computationally Relevant Typological Features
|
|
|
|
In: http://faculty.washington.edu/wlewis2/papers/LewisXia-ijcnlp08t-06.pdf (2008)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Automatically Identifying Computationally Relevant Typological Features
|
|
|
|
In: http://aclweb.org/anthology/I/I08/I08-2093.pdf (2008)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Repurposing theoretical linguistic data for tool development and search
|
|
|
|
In: http://aclweb.org/anthology/I/I08/I08-1069.pdf (2008)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Multilingual Structural Projection across Interlinearized Text
|
|
|
|
In: http://faculty.washington.edu/fxia/mpapers/NAACL07.pdf (2007)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
ODIN: A Model for Adapting and Enriching Legacy Infrastructure
|
|
|
|
In: http://faculty.washington.edu/wlewis2/papers/ODIN-eH06.pdf (2006)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Linguistics In The Internet Age: Tools And Fair Use
|
|
|
|
In: http://emeld.org/workshop/2006/papers/lewis.pdf (2006)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
ODIN: A Model for Adapting and Enriching Legacy Infrastructure
|
|
|
|
In: http://emeld.org/school/readingroom/odin.pdf (2006)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
The GOLD Community of Practice - An Infrastructure for Linguistic Data on the Web
|
|
|
|
In: http://faculty.washington.edu/wlewis2/papers/FarLew06.pdf (2005)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
The GOLD Community of Practice: An infrastructure for linguistic data on the Web
|
|
|
|
In: http://emeld.org/workshop/2005/papers/FarLew-emeld.pdf (2005)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
An Ontology for Linguistic Annotation
|
|
|
|
In: http://saussure.linguistlist.org/cfdocs/emeld/workshop/2002/presentations/arizona/AAAI_paper.pdf.pdf (2002)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
An ontology for linguistic annotation
|
|
|
|
In: http://aaai.org/Papers/Workshops/2002/WS-02-16/WS02-16-002.pdf (2002)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
A Common Ontology for Linguistic Concepts
|
|
|
|
In: http://faculty.washington.edu/wlewis2/papers/FarLewLang02a.pdf (2002)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Improving Dependency Parsing with Interlinear Glossed Text and Syntactic Projection
|
|
|
|
In: http://aclweb.org/anthology/C/C12/C12-2037.pdf
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Enriching ODIN
|
|
|
|
In: http://www.lrec-conf.org/proceedings/lrec2014/pdf/1072_Paper.pdf
|
|
BASE
|
|
Show details
|
|
|
| 18 |
The Problems of Language Identification within Hugely Multilingual Data Sets
|
|
|
|
In: http://www.lrec-conf.org/proceedings/lrec2010/pdf/921_Paper.pdf
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Linguistics in the Internet Age: Tools and the Fair Use of Digital Data
|
|
|
|
In: http://faculty.washington.edu/farrar/documents/review/LewFarLang_review.pdf
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Parsing, Projecting & Prototypes: Repurposing Linguistic Data on the Web
|
|
|
|
In: http://faculty.washington.edu/fxia/mpapers/EACL09_demo.pdf
|
|
BASE
|
|
Show details
|
|
|
|
|
