Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jakob Elming"'
Publikováno v:
WASSA@ACL
While various approaches to domain adaptation exist, the majority of them requires knowledge of the target domain, and additional data, preferably labeled. For a language like English, it is often feasible to match most of those conditions, but in lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a7e9a85074e755285dafb3d0708358b
http://hdl.handle.net/11565/4006647
http://hdl.handle.net/11565/4006647
Autor:
Jakob Elming, Anders Johanssen, Sigrid Klerke, Barbara Plank, Anders Søgaard, Héctor Martínez Alonso, Dirk Hovy, Natalie Schluter
Publikováno v:
SemEval@COLING
In this shared task paper for SemEval2014 Task 8, we show that most semantic structures can be approximated by trees through a series of almost bijective graph transformations. We transform input graphs, apply off-the-shelf methods from syntactic par
Autor:
Jakob Elming, Nizar Habash
Publikováno v:
SEMITIC@EACL
New York University Scholars
New York University Scholars
We investigate syntactic reordering within an English to Arabic translation task. We extend a pre-translation syntactic reordering approach developed on a close language pair (English-Danish) to the distant language pair, English-Arabic. We achieve s
Autor:
Jakob Elming
Publikováno v:
SSST@ACL
COLING
COLING
We present a novel approach to word reordering which successfully integrates syntactic structural knowledge with phrase-based SMT. This is done by constructing a lattice of alternatives based on automatically learned probabilistic syntactic rules. In
Autor:
Philip Diderichsen, Jakob Elming
Publikováno v:
ACL
We report on an investigation of the pragmatic category of topic in Danish dialog and its correlation to surface features of NPs. Using a corpus of 444 utterances, we trained a decision tree system on 16 features. The system achieved near-human perfo
Autor:
Nizar Habash, Jakob Elming
Publikováno v:
New York University Scholars
HLT-NAACL (Short Papers)
HLT-NAACL (Short Papers)
We present an approach to using multiple preprocessing schemes to improve statistical word alignments. We show a relative reduction of alignment error rate of about 38%.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e76d4fa4c15daf2d208630420a776b9
https://nyuscholars.nyu.edu/en/publications/ec0d1c36-5573-42eb-8578-9e4f1f780ee7
https://nyuscholars.nyu.edu/en/publications/ec0d1c36-5573-42eb-8578-9e4f1f780ee7