Summary of the paper
| Title | Evaluation of Machine Translation Errors in English and Iraqi Arabic |
|---|---|
| Authors | Sherri Condon, Dan Parvaz, John Aberdeen, Christy Doran, Andrew Freeman and Marwan Awad |
| Abstract | Errors in machine translations of English-Iraqi Arabic dialogues were analyzedat two different points in the systems? development using HTER methods toidentify errors and human annotations to refine TER annotations. The analyseswere performed on approximately 100 translations into each language from 4translation systems collected at two annual evaluations. Although thefrequencies of errors in the more mature systems were lower, the proportions oferror types exhibited little change. Results include high frequencies ofpronoun errors in translations to English, high frequencies of subject personinflection in translations to Iraqi Arabic, similar frequencies of word ordererrors in both translation directions, and very low frequencies of polarityerrors. The problems with many errors can be generalized as the need to insertlexemes not present in the source or vice versa, which includes errors inmulti-word expressions. Discourse context will be required to resolve someproblems with deictic elements like pronouns. |
| Language | Dialogue |
| Topics | Machine Translation, SpeechToSpeech Translation, Evaluation methodologies, Dialogue |
Full paper  |
Evaluation of Machine Translation Errors in English and Iraqi Arabic |
| Bibtex | @InProceedings{CONDON10.106, author = {Sherri Condon, Dan Parvaz, John Aberdeen, Christy Doran, Andrew Freeman and Marwan Awad}, title = {Evaluation of Machine Translation Errors in English and Iraqi Arabic}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |