DE eng

Search in the Catalogues and Directories

Hits 1 – 6 of 6

1
DCU-Paris13 systems for the SANCL 2012 shared task
In: Le Roux, Joseph, Foster, Jennifer orcid:0000-0002-7789-4853 , Wagner, Joachim orcid:0000-0002-8290-3849 , Samad Zadeh Kaljahi, Rasoul and Bryl, Anton (2012) DCU-Paris13 systems for the SANCL 2012 shared task. In: The NAACL 2012 First Workshop on Syntactic Analysis of Non-Canonical Language (SANCL), 7-8 Jun 2012, Montreal, Quebec, Canada. (2012)
BASE
Show details
2
Improving dependency label accuracy using statistical post-editing: A cross-framework study
In: Cetinoglu, Ozlem, Bryl, Anton, Foster, Jennifer orcid:0000-0002-7789-4853 and van Genabith, Josef orcid:0000-0003-1322-7944 (2011) Improving dependency label accuracy using statistical post-editing: A cross-framework study. In: International Conference on Dependency Linguistics (DepLing), 5-7 Sept 2011, Barcelona, Spain. (2011)
BASE
Show details
3
f-align: An open-source alignment tool for LFG f-structures
In: Bryl, Anton and van Genabith, Josef orcid:0000-0003-1322-7944 (2010) f-align: An open-source alignment tool for LFG f-structures. In: AMTA, 31 Oct - 4th Nov 2010, Denver, Colorado. (2010)
BASE
Show details
4
Two approaches to automatic matching of atomic grammatical features in LFG
In: Bryl, Anton and van Genabith, Josef orcid:0000-0003-1322-7944 (2010) Two approaches to automatic matching of atomic grammatical features in LFG. In: LFG10 Conference, 18-20 July 2010, Ottowa, Canada. (2010)
Abstract: The alignment of a bilingual corpus is an important step in data preparation for data-driven machine translation. LFG f-structures provide bilexical labelled dependencies in the form of lemmas and core grammatical functions linking those lemmas, but also important grammatical features (TENSE, NUMBER, CASE, etc.) representing morphological and semantic information. These grammatical features can often be translated independently from the lemmas or words. It is therefore of practical interest to develop methods that align grammatical features which can be considered translations of each other (e.g. the number features of the corresponding words in the source and target parts of the corpus) in data-driven LFG-based MT. In a parallel grammar development scenario, such as ParGram, this is to a large extent captured through manually hardcoding the correspondences in the hand-crafted grammars, using similar or identical feature names for similar phenomena across languages. However, for a completely automatic learning method it is desirable to establish these correspondences without human assistance. In this paper we present and evaluate two approaches to the automatic identification of correspondences between atomic features of LFG (and similar) grammars for different languages. The methods can be used to evaluate the correspondence between feature names in hand-crafted parallel grammars or find correspondences between features in grammars for different languages where feature alignments are not known.
Keyword: LFG Grammars; Machine translating
URL: http://doras.dcu.ie/16016/
BASE
Hide details
5
Guessing the grammatical function of a non-root f-structure in LFG
In: Bryl, Anton, van Genabith, Josef and Graham, Yvette orcid:0000-0003-1322-7944 (2009) Guessing the grammatical function of a non-root f-structure in LFG. In: IWPT 2009 - 11th International Conference on Parsing Technologies, 7-9 October 2009, Paris, France. (2009)
BASE
Show details
6
F-structure transfer-based statistical machine translation
In: Graham, Yvette, van Genabith, Josef orcid:0000-0003-1322-7944 and Bryl, Anton (2009) F-structure transfer-based statistical machine translation. In: Lexical Functional Grammar 2009, 13-16 July 2009, Cambridge, UK. (2009)
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
6
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern