| 1 |
Generative vs Discriminative Approaches to Entity Extraction from Label Deficient Data
|
|
|
|
In: http://www.cavi.univ-paris3.fr/lexicometrica/jadt/jadt2004/pdf/JADT_049.pdf (2004)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Word-Sequence Kernels
|
|
|
|
In: http://www.jmlr.org/papers/volume3/cancedda03a/cancedda03a.ps.gz (2003)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Word-sequence kernels
|
|
|
|
In: http://www.fizyka.umk.pl/ftp/incoming/duch/Kernele/JMLR-WordSequenceKernels-Cancedda03a.pdf (2003)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Learning computational grammars
|
|
|
|
In: http://acl.ldc.upenn.edu/W/W01/W01-0712.pdf (2001)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Learning Computational Grammars
|
|
|
|
In: http://lcg-www.uia.ac.be/lcg/texts/./pdf/nerbonne.conll2001.pdf (2001)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Learning computational grammars
|
|
|
|
In: http://www.cnts.ua.ac.be/papers/2001/conlld01.pdf (2001)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Learning computational grammars
|
|
|
|
In: http://www.cnts.ua.ac.be/conll2001/pdf/09704ner.pdf (2001)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Learning computational grammars
|
|
|
|
In: http://staff.science.uva.nl/~erikt/papers/conll2001d.pdf (2001)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Experiments with Corpus-based LFG Specialization
|
|
|
|
In: http://acl.ldc.upenn.edu/A/A00/A00-1028.pdf (2000)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Corpus-based Grammar Specialization
|
|
|
|
In: http://lcg-www.uia.ac.be/lcg/texts/./ps/cancedda.conll2000.ps.gz (2000)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
SAX: Generating Hypertext from SADT models
|
|
|
|
In: ftp://hermes.dis.uniroma1.it/pub/cancedda/Cancedda-et-al-97.ps.gz (1997)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
SAX: Generating Hypertext from SADT models
|
|
|
|
In: ftp://hermes.dis.uniroma1.it/pub/cancedda/Cancedda-et-al-97b.ps.gz (1997)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Integrating Shallow and Linguistic Techniques for Information Extraction from Text
|
|
|
|
In: http://ecate.itc.it:1025/cirave/paperi/AIIA95.ps (1995)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Asymmetric Term Alignment with Selective Contiguity Constraints by Multi-Tape Automata
|
|
|
|
In: http://opus.kobv.de/ubp/volltexte/2008/2711/pdf/fsmnlp07proc04.pdf
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Spoken Language Systems
|
|
|
|
In: http://www.mt-archive.info/AMTA-2010-Roth.pdf
|
|
BASE
|
|
Show details
|
|
|
| 18 |
2011. Productive Generation of Compound Words in Statistical Machine Translation
|
|
|
|
In: http://wing.comp.nus.edu.sg/~antho/J/J13/J13-4009.pdf
|
|
BASE
|
|
Show details
|
|
|
| 19 |
A Hybrid Approach to Hypertext Generation
|
|
|
|
In: http://ecate.itc.it:1024/kamstrup/sax/aiia.ps.gz
|
|
BASE
|
|
Show details
|
|
|
| 20 |
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-76689 Generation of Compound Words in Statistical Machine Translation into Compounding Languages
|
|
|
|
In: http://liu.diva-portal.org/smash/get/diva2:515868/FULLTEXT01.pdf
|
|
Abstract:
In this article we investigate statistical machine translation (SMT) into Germanic languages, with a focus on compound processing. Our main goal is to enable the generation of novel compounds that have not been seen in the training data. We adopt a split-merge strategy, where compounds are split before training the SMT system, and merged after the translation step. This approach reduces sparsity in the training data, but runs the risk of placing translations of compound parts in non-consecutive positions. It also requires a postprocessing step of compound merging, where compounds are reconstructed in the translation output. We present a method for increasing the chances that components that should be merged are translated into contiguous positions and in the right order and show that it can lead to improvements both by direct inspection and in terms of standard translation evaluation metrics. We also propose several new methods for compound merging, based on heuristics and machine learning, which outperform previously suggested algorithms. These methods can produce novel compounds and a translation with at least the same overall quality as the baseline. For all subtasks we show that it is useful to include part-of-speech based information in the translation process, in order to handle compounds. 1.
|
|
URL: http://liu.diva-portal.org/smash/get/diva2:515868/FULLTEXT01.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.429.1153
|
|
BASE
|
|
Hide details
|
|
|
|
|
