| 1 |
Is all that glitters in MT quality estimation really gold standard?
|
|
|
|
In: Graham, Yvette, Baldwin, Timothy, Dowling, Meghan orcid:0000-0003-1637-4923 , Eskevich, Maria, Lynn, Teresa and Tounsi, Lamia (2016) Is all that glitters in MT quality estimation really gold standard? In: 26th International Conference on Computational Linguistics, 11-17 Dec 2016, Osaka, Japan. ISBN 978-4-87974-702-0 (2016)
|
|
Abstract:
Human-targeted metrics provide a compromise between human evaluation of machine translation, where high inter-annotator agreement is difficult to achieve, and fully automatic metrics, such as BLEU or TER, that lack the validity of human assessment. Human-targeted translation edit rate (HTER) is by far the most widely employed human-targeted metric in machine translation, commonly employed, for example, as a gold standard in evaluation of quality estimation. Original experiments justifying the design of HTER, as opposed to other possible formulations, were limited to a small sample of translations and a single language pair, however, and this motivates our re-evaluation of a range of human-targeted metrics on a substantially larger scale. Results show significantly stronger correlation with human judgment for HBLEU over HTER for two of the nine language pairs we include and no significant difference between correlations achieved by HTER and HBLEU for the remaining language pairs. Finally, we evaluate a range of quality estimation systems employing HTER and direct assessment (DA) of translation adequacy as gold labels, resulting in a divergence in system rankings, and propose employment of DA for future quality estimation evaluations.
|
|
Keyword:
Machine translating
|
|
URL: http://doras.dcu.ie/23608/
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
DCU: aspect-based polarity classification for SemEval task 4
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 , Arora, Piyush orcid:0000-0002-4261-2860 , Cortes, Santiago, Barman, Utsab, Bogdanova, Dasha, Foster, Jennifer orcid:0000-0002-7789-4853 and Tounsi, Lamia (2014) DCU: aspect-based polarity classification for SemEval task 4. In: International Workshop on Semantic Evaluation (SemEval-2014), 23-24 Aug 2014, Dublin, Ireland. ISBN 978-1-941643-24-2 (2014)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Cross-lingual transfer parsing for low-resourced languages: an Irish case study
|
|
|
|
In: Lynn, Teresa, Foster, Jennifer orcid:0000-0002-7789-4853 , Dras, Mark orcid:0000-0001-9908-7182 and Tounsi, Lamia (2014) Cross-lingual transfer parsing for low-resourced languages: an Irish case study. In: First Celtic Language Technology Workshop, 23 Aug 2014, Dublin, Ireland. (2014)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Cross-lingual transfer parsing for low-resourced languages : an Irish case study
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Sentiment analysis of political tweets: towards an accurate classifier
|
|
|
|
In: Bakliwal, Akshat, Foster, Jennifer orcid:0000-0002-7789-4853 , van der Puil, Jennifer, O'Brien, Ron, Tounsi, Lamia and Hughes, Mark (2013) Sentiment analysis of political tweets: towards an accurate classifier. In: NAACL Workshop on Language Analysis in Social Media, 13 June 2013, Atlanta, GA. (2013)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
An automatically built named entity lexicon for Arabic
|
|
|
|
In: Attia, Mohammed, Toral, Antonio orcid:0000-0003-2357-2960 , Tounsi, Lamia, Monachini, Monica and van Genabith, Josef orcid:0000-0003-1322-7944 (2010) An automatically built named entity lexicon for Arabic. In: LREC 2010 - 7th conference on International Language Resources and Evaluation, 17-23 May 2010, Valletta, Malta. (2010)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Arabic parsing using grammar transforms
|
|
|
|
In: Tounsi, Lamia and van Genabith, Josef orcid:0000-0003-1322-7944 (2010) Arabic parsing using grammar transforms. In: LREC 2010 - 7th conference on International Language Resources and Evaluation, 17-23 May 2010, Valletta, Malta. (2010)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Statistical parsing of morphologically rich languages (SPMRL): what, how and whither
|
|
|
|
In: Tsarfaty, Reut, Seddah, Djamé, Goldberg, Yoav, Kübler, Sandra, Candito, Marie, Foster, Jennifer orcid:0000-0002-7789-4853 , Versley, Yannick, Rehbein, Ines and Tounsi, Lamia (2010) Statistical parsing of morphologically rich languages (SPMRL): what, how and whither. In: Proceedings of the First Workshop on Statistical Parsing of Morphologically Rich Languages, 5 Jun 2010, Los Angeles, CA. (2010)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Automatic extraction of Arabic multiword expressions
|
|
|
|
In: Attia, Mohammed, Tounsi, Lamia, Pecina, Pavel, van Genabith, Josef orcid:0000-0003-1322-7944 and Toral, Antonio (2010) Automatic extraction of Arabic multiword expressions. In: the 7th Conference on Language Resources and Evaluation (LREC 2010)., May 2010., Valletta (Malta). (2010)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Handling unknown words in statistical latent-variable parsing models for Arabic, English and French
|
|
|
|
In: Attia, Mohammed, Foster, Jennifer orcid:0000-0002-7789-4853 , Hogan, Deirdre, Le Roux, Joseph, Tounsi, Lamia and van Genabith, Josef orcid:0000-0003-1322-7944 (2010) Handling unknown words in statistical latent-variable parsing models for Arabic, English and French. In: SPMRL 2010 - 1st Workshop on Statistical Parsing of Morphologically-Rich Languages at NAACL HLT 2010, 5 June 2010, Los Angeles, CA, USA. (2010)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Handling Unknown Words in Statistical Latent-Variable Parsing Models for Arabic, English and French
|
|
|
|
In: Proceedings of the First Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL 2010) ; First Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL 2010) ; https://hal.archives-ouvertes.fr/hal-00702414 ; First Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL 2010), 2010, United States. pp.67-75 (2010)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither
|
|
|
|
In: Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages ; https://hal.inria.fr/inria-00525751 ; Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages, 2010, Los Angeles, United States. pp.1--12 (2010)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Parsing Arabic using treebank-based LFG resources
|
|
|
|
In: Tounsi, Lamia, Attia, Mohammed and van Genabith, Josef orcid:0000-0003-1322-7944 (2009) Parsing Arabic using treebank-based LFG resources. In: Lexical Functional Grammar 2009, 13-16 July 2009, Cambridge, UK. (2009)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Automatic treebank-based acquisition of Arabic LFG dependency structures
|
|
|
|
In: Tounsi, Lamia, Attia, Mohammed and van Genabith, Josef orcid:0000-0003-1322-7944 (2009) Automatic treebank-based acquisition of Arabic LFG dependency structures. In: EACL 2009 Workshop on Computational Approaches to Semitic Languages, 31 March 2009, Athens, Greece. (2009)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Compression method for natural language automata
|
|
|
|
In: Finite-State Methods and Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-01024076 ; Finite-State Methods and Natural Language Processing, 2008, Ispra, Italy. pp.146-157 (2008)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Compression de dictionnaires électroniques
|
|
|
|
In: Neuvièmes journées internationales d'analyse statistique des données textuelles ; https://hal.archives-ouvertes.fr/hal-01030743 ; Neuvièmes journées internationales d'analyse statistique des données textuelles, 2008, Lyon, France. pp.1103-1114 (2008)
|
|
BASE
|
|
Show details
|
|
|
|
|
