DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 32

1
Efficient techniques for streaming cross document coreference resolution
Shrimpton, Luke William. - : The University of Edinburgh, 2017
BASE
Show details
2
Learning to hash for large scale image retrieval
Moran, Sean James. - : The University of Edinburgh, 2016
BASE
Show details
3
Real-time detection, tracking, and monitoring of automatically discovered events in social media
BASE
Show details
4
Real-Time Detection, Tracking, and Monitoring of Automatically Discovered Events in Social Media
von Lunen, Alexander; McCreadie, Richard; Ciravegna, Fabio. - : Association for Computational Linguistics, 2014
BASE
Show details
5
Introducing corpus-based rules and algorithms in a rule-based machine translation system
Dugast, Loic. - : The University of Edinburgh, 2013
BASE
Show details
6
Real-time event detection in massive streams
Petrovic, Sasa. - : The University of Edinburgh, 2013
BASE
Show details
7
Opinion Retrieval in Twitter
In: Proceedings of the International AAAI Conference on Web and Social Media; Vol. 6 No. 1 (2012): Sixth International AAAI Conference on Weblogs and Social Media ; 2334-0770 ; 2162-3449 (2012)
BASE
Show details
8
Improving statistical machine translation with linguistic information
Hoang, Hieu. - : The University of Edinburgh, 2011
BASE
Show details
9
Reordering metrics for statistical machine translation
Birch, Alexandra. - : The University of Edinburgh, 2011
Abstract: Natural languages display a great variety of different word orders, and one of the major challenges facing statistical machine translation is in modelling these differences. This thesis is motivated by a survey of 110 different language pairs drawn from the Europarl project, which shows that word order differences account for more variation in translation performance than any other factor. This wide ranging analysis provides compelling evidence for the importance of research into reordering. There has already been a great deal of research into improving the quality of the word order in machine translation output. However, there has been very little analysis of how best to evaluate this research. Current machine translation metrics are largely focused on evaluating the words used in translations, and their ability to measure the quality of word order has not been demonstrated. In this thesis we introduce novel metrics for quantitatively evaluating reordering. Our approach isolates the word order in translations by using word alignments. We reduce alignment information to permutations and apply standard distance metrics to compare the word order in the reference to that of the translation. We show that our metrics correlate more strongly with human judgements of word order quality than current machine translation metrics. We also show that a combined lexical and reordering metric, the LRscore, is useful for training translation model parameters. Humans prefer the output of models trained using the LRscore as the objective function, over those trained with the de facto standard translation metric, the BLEU score. The LRscore thus provides researchers with a reliable metric for evaluating the impact of their research on the quality of word order.
Keyword: metrics; standard distance metrics; statistical machine translation; word order
URL: http://hdl.handle.net/1842/5024
BASE
Hide details
10
Stream-based statistical machine translation
Levenberg, Abby D.. - : The University of Edinburgh, 2011
BASE
Show details
11
Cyril Goutte, Nicola Cancedda, Marc Dymetman, George Foster (eds.): Learning Machine Translation [Rezension]
In: Natural language engineering. - Cambridge : Cambridge University Press 16 (2010) 1, 99-100
BLLDB
OLC Linguistik
Show details
12
Metrics for MT evaluation: evaluating reordering
In: Machine translation. - Dordrecht [u.a.] : Springer Science + Business Media 24 (2010) 1, 15-26
BLLDB
OLC Linguistik
Show details
13
Machine Translation for Twitter
Jehl, Laura Elisabeth. - : The University of Edinburgh, 2010
BASE
Show details
14
Automatic recognition of multiparty human interactions using dynamic Bayesian networks
Dielmann, Alfred. - : The University of Edinburgh, 2009
BASE
Show details
15
Wide-coverage parsing for Turkish
Çakici, Ruket. - : The University of Edinburgh, 2009
BASE
Show details
16
Active learning and logarithmic opinion pools for HPSG parse selection
In: Natural language engineering. - Cambridge : Cambridge University Press 14 (2008) 2, 191-222
BLLDB
OLC Linguistik
Show details
17
Diversity in logarithmic opinion pools
In: Lingvisticae investigationes. - Amsterdam : Benjamins 30 (2007) 1, 27-47
BLLDB
Show details
18
Re-evaluating the role of BLEU in machine translation research
In: Association for Computational Linguistics / European Chapter. Conference of the European Chapter of the Association for Computational Linguistics. - Menlo Park, Calif. : ACL 11 (2006), 249-256
BLLDB
Show details
19
Logarithmic Opinion Pools for Conditional Random Fields
BASE
Show details
20
Scaling conditional random fields using error correcting codes
BASE
Show details

Page: 1 2

Catalogues
1
0
3
0
0
0
0
Bibliographies
10
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
21
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern