Evaluation of a Machine Translation System for Low Resource Languages: METIS-II

Vincent Vandeghinste; Peter Dirix; Ineke Schuurmann; Stella Markantonatou; Sokratis Sofianopoulos; Marina Vassilou; Olga Yannoutsou; Toni Badia; Maite Melero; Gemma Boleda; Michael Carl; Paul Schmidt

Evaluation of a Machine Translation System for Low Resource Languages: METIS-II

Vincent Vandeghinste, Peter Dirix, Ineke Schuurmann, Stella Markantonatou, Sokratis Sofianopoulos, Marina Vassilou, Olga Yannoutsou, Toni Badia, Maite Melero, Gemma Boleda, Michael Carl, Paul Schmidt

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Abstrakt

In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged developing a data-driven approach in which no parallel corpus is required, and in which no full parser or extensive rule sets are needed. We describe evalution on a development test set and on a test set coming from Europarl, and compare our results with SYSTRAN. We also provide some further analysis, researching the impact of the number and source of the reference translations and analysing the results according to test text type. The results are expectably lower for the METIS system, but not at an unatainable distance from a mature system like SYSTRAN.

Originalsprog	Engelsk
Titel	The LREC 2008 Proceedings : The Sixth International Conference on Language Resources and Evaluation (LREC'08)
Redaktører	Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias
Antal sider	8
Udgivelsessted	Paris
Forlag	European Language Resources Association
Publikationsdato	2008
Sider	449-456
ISBN (Trykt)	2951740840
Status	Udgivet - 2008
Udgivet eksternt	Ja
Begivenhed	The 6th International Conference on Language Resources and Evaluation. LREC 2008 - Marrakech, Marokko Varighed: 28 maj 2008 → 30 maj 2008 Konferencens nummer: 6 http://www.lrec-conf.org/lrec2008/

Konference

Konference	The 6th International Conference on Language Resources and Evaluation. LREC 2008
Nummer	6
Land/Område	Marokko
By	Marrakech
Periode	28/05/2008 → 30/05/2008
Internetadresse	http://www.lrec-conf.org/lrec2008/

Adgang til dokumentet

http://www.lrec-conf.org/proceedings/lrec2008/pdf/116_paper.pdfLicens: CC BY-NC

CBS fjernadgang

Fuld tekst

Handle.net

Persistent link

Citationsformater

Vandeghinste, V., Dirix, P., Schuurmann, I., Markantonatou, S., Sofianopoulos, S., Vassilou, M., Yannoutsou, O., Badia, T., Melero, M., Boleda, G., Carl, M., & Schmidt, P. (2008). Evaluation of a Machine Translation System for Low Resource Languages: METIS-II. I N. Calzolari, K. Choukri, B. Maegaard, J. Mariani, J. Odijk, S. Piperidis, & D. Tapias (red.), The LREC 2008 Proceedings: The Sixth International Conference on Language Resources and Evaluation (LREC'08) (s. 449-456). European Language Resources Association. http://www.lrec-conf.org/proceedings/lrec2008/pdf/116_paper.pdf

Vandeghinste, Vincent ; Dirix, Peter ; Schuurmann, Ineke et al. / Evaluation of a Machine Translation System for Low Resource Languages : METIS-II. The LREC 2008 Proceedings: The Sixth International Conference on Language Resources and Evaluation (LREC'08). red. / Nicoletta Calzolari ; Khalid Choukri ; Bente Maegaard ; Joseph Mariani ; Jan Odijk ; Stelios Piperidis ; Daniel Tapias. Paris : European Language Resources Association, 2008. s. 449-456

@inproceedings{e59513f0d02611dd8e8d000ea68e967b,

title = "Evaluation of a Machine Translation System for Low Resource Languages: METIS-II",

abstract = "In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged developing a data-driven approach in which no parallel corpus is required, and in which no full parser or extensive rule sets are needed. We describe evalution on a development test set and on a test set coming from Europarl, and compare our results with SYSTRAN. We also provide some further analysis, researching the impact of the number and source of the reference translations and analysing the results according to test text type. The results are expectably lower for the METIS system, but not at an unatainable distance from a mature system like SYSTRAN.",

keywords = "METIS-II",

author = "Vincent Vandeghinste and Peter Dirix and Ineke Schuurmann and Stella Markantonatou and Sokratis Sofianopoulos and Marina Vassilou and Olga Yannoutsou and Toni Badia and Maite Melero and Gemma Boleda and Michael Carl and Paul Schmidt",

year = "2008",

language = "English",

isbn = "2951740840",

pages = "449--456",

editor = "Nicoletta Calzolari and Khalid Choukri and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis and Daniel Tapias",

booktitle = "The LREC 2008 Proceedings",

publisher = "European Language Resources Association",

address = "France",

note = "The 6th International Conference on Language Resources and Evaluation. LREC 2008 ; Conference date: 28-05-2008 Through 30-05-2008",

url = "http://www.lrec-conf.org/lrec2008/",

}

Vandeghinste, V, Dirix, P, Schuurmann, I, Markantonatou, S, Sofianopoulos, S, Vassilou, M, Yannoutsou, O, Badia, T, Melero, M, Boleda, G, Carl, M & Schmidt, P 2008, Evaluation of a Machine Translation System for Low Resource Languages: METIS-II. i N Calzolari, K Choukri, B Maegaard, J Mariani, J Odijk, S Piperidis & D Tapias (red), The LREC 2008 Proceedings: The Sixth International Conference on Language Resources and Evaluation (LREC'08). European Language Resources Association, Paris, s. 449-456, The 6th International Conference on Language Resources and Evaluation. LREC 2008, Marrakech, Marokko, 28/05/2008. <http://www.lrec-conf.org/proceedings/lrec2008/pdf/116_paper.pdf>

Evaluation of a Machine Translation System for Low Resource Languages : METIS-II. / Vandeghinste, Vincent; Dirix, Peter; Schuurmann, Ineke et al.

The LREC 2008 Proceedings: The Sixth International Conference on Language Resources and Evaluation (LREC'08). red. / Nicoletta Calzolari; Khalid Choukri; Bente Maegaard; Joseph Mariani; Jan Odijk; Stelios Piperidis; Daniel Tapias. Paris : European Language Resources Association, 2008. s. 449-456.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Evaluation of a Machine Translation System for Low Resource Languages

T2 - The 6th International Conference on Language Resources and Evaluation. LREC 2008

AU - Vandeghinste, Vincent

AU - Dirix, Peter

AU - Schuurmann, Ineke

AU - Markantonatou, Stella

AU - Sofianopoulos, Sokratis

AU - Vassilou, Marina

AU - Yannoutsou, Olga

AU - Badia, Toni

AU - Melero, Maite

AU - Boleda, Gemma

AU - Carl, Michael

AU - Schmidt, Paul

N1 - Conference code: 6

PY - 2008

Y1 - 2008

N2 - In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged developing a data-driven approach in which no parallel corpus is required, and in which no full parser or extensive rule sets are needed. We describe evalution on a development test set and on a test set coming from Europarl, and compare our results with SYSTRAN. We also provide some further analysis, researching the impact of the number and source of the reference translations and analysing the results according to test text type. The results are expectably lower for the METIS system, but not at an unatainable distance from a mature system like SYSTRAN.

AB - In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged developing a data-driven approach in which no parallel corpus is required, and in which no full parser or extensive rule sets are needed. We describe evalution on a development test set and on a test set coming from Europarl, and compare our results with SYSTRAN. We also provide some further analysis, researching the impact of the number and source of the reference translations and analysing the results according to test text type. The results are expectably lower for the METIS system, but not at an unatainable distance from a mature system like SYSTRAN.

KW - METIS-II

M3 - Article in proceedings

SN - 2951740840

SP - 449

EP - 456

BT - The LREC 2008 Proceedings

A2 - Calzolari, Nicoletta

A2 - Choukri, Khalid

A2 - Maegaard, Bente

A2 - Mariani, Joseph

A2 - Odijk, Jan

A2 - Piperidis, Stelios

A2 - Tapias, Daniel

PB - European Language Resources Association

CY - Paris

Y2 - 28 May 2008 through 30 May 2008

ER -

Vandeghinste V, Dirix P, Schuurmann I, Markantonatou S, Sofianopoulos S, Vassilou M et al. Evaluation of a Machine Translation System for Low Resource Languages: METIS-II. I Calzolari N, Choukri K, Maegaard B, Mariani J, Odijk J, Piperidis S, Tapias D, red., The LREC 2008 Proceedings: The Sixth International Conference on Language Resources and Evaluation (LREC'08). Paris: European Language Resources Association. 2008. s. 449-456