--- title: "Problems of Arabic Machine Translation — paper by Izwaini (2006)" description: "The paper presents a qualitative error analysis of three free online machine translation services for… 13 references, cited by 1 paper here." authors: ["Sattar Izwaini"] year: 2006 venue: "Proceedings of the International Conference on the Challenge of Arabic for NLP/MT" source: "https://aclanthology.org/2006.bcs-1.11/" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/izwaini-2006-problems-arabic-machine-translation-evaluation/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/izwaini-2006-problems-arabic-machine-translation-evaluation/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2006](https://md.research.elamur.ai/free/en/papers/2006/page/2/) / Problems of Arabic Machine Translation: Evaluation of Three Systems # Problems of Arabic Machine Translation: Evaluation of Three Systems **Authors:** Sattar Izwaini · **Year:** 2006 · **Venue:** [Proceedings of the International Conference on the Challenge of Arabic for NLP/MT](https://md.research.elamur.ai/free/en/venues/bcs/) ([International Conference on the Challenge of Arabic for NLP/MT 2006](https://md.research.elamur.ai/free/en/venues/bcs/2006/)) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/2006.bcs-1.11/) · [PDF](https://aclanthology.org/2006.bcs-1.11.pdf) · [OpenAlex](https://openalex.org/W2132987078) **Citations:** 20 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/izwaini-2006-problems-arabic-machine-translation-evaluation/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper presents a qualitative error analysis of three free online machine translation services for Arabic and English: Google, Sakhr (its Tarjim site, run in practice through Sakhr's SET engine) and Systran. The input came from an introductory translation course at Abu Dhabi University. These were 76 English and 46 Arabic texts that grow from one-word commands to specialised paragraphs. Literary material was left out because the author considers creative writing an unfair test for MT. Outputs were judged on readability, informativeness and closeness to a human translation. Errors were then sorted into linguistic categories and traced to likely causes. In the Arabic-to-English direction, Sakhr and Google each produced fully acceptable output for about a third of texts, while Systran rarely did. Most errors came from the missing diacritics in Arabic script, gaps in the lexicon, mishandled attached clitics and proper names that were translated as ordinary words. The author argues that systems should use the lexical environment and collocations to choose equivalents, and should aim to reduce post-editing effort rather than settle for gist-level output. ## Key points - Corpus: 76 English and 46 Arabic texts from a Fall 2005–2006 translation course, ordered by rising length and complexity, with literary texts excluded. - Fully correct Arabic→English translations: Sakhr 16 (34.7%), Google 15 (32.6%), Systran 2 (4.3%). - Google dropped content words outright in 10 cases (21.7% of its translations), even though such words should at least have been transliterated. - Unvocalised homographs caused many errors: - choosing between world and scientist; - choosing between active and passive verb forms; - picking the wrong person on past-tense verbs. - Regional spelling variants (the Egyptian dotless final ya) and attached prefixes or pronouns also broke dictionary lookup. - Personal and place names were rendered by their meanings. One example is the name Rasheed, which Sakhr turned into "Rosetta" and Systran into "rational". The author also judged Systran's output too literal to post-edit cheaply. ## Interesting ideas - When a word went untranslated, the author removed the article, prefix or pronoun and resubmitted; the system then translated it, which showed the fault lay in clitic handling rather than the lexicon. - Some candidate morphological analyses can be ruled out on grammar alone, such as a verb-only pronoun form attached to a noun in the misparse of "Sydney". - Neighbouring proper names can serve as evidence that an ambiguous token is itself part of a name and should be kept, not translated by its meaning. - The author repeatedly suggests choosing a word's sense by checking which meaning fits the words and collocations around it. - The evaluation used graded course material, excluded poetry as out of scope and measured quality by how much post-editing a human would need. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (learn): Mova's evaluation could perturb failing inputs by stripping affixes or splitting contractions to tell vocabulary gaps apart from segmentation bugs before writing repair rules. - **I2** (tokens): the morphology stage could apply hard compatibility constraints to drop impossible segmentations before tagging, so errors like this never reach the parser. - **I3** (world): entity building could use adjacent recognised names to keep surname-like common nouns as names, rather than reading them as properties or objects. - **I4** (frames): VerbNet class and role selection could score each candidate sense against its co-occurring arguments and prefer the one whose collocates fit. - **I5** (back): generated or translated text could be scored on graded inputs by estimated repair effort, giving a more practical quality measure than a simple pass/fail. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Abu Dhabi University](https://md.research.elamur.ai/free/en/universities/abu-dhabi-university/) — University, Abu Dhabi, United Arab Emirates · 2 works · 38 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works 🧭 Topics (2): [🔁 Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) · 1,087 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works ## Cite Cite as: Sattar Izwaini. 2006. Problems of Arabic Machine Translation: Evaluation of Three Systems. Proceedings of the International Conference on the Challenge of Arabic for NLP/MT. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{izwaini2006problems, title = {{Problems of Arabic Machine Translation: Evaluation of Three Systems}}, author = {Sattar Izwaini}, booktitle = {Proceedings of the International Conference on the Challenge of Arabic for NLP/MT}, year = {2006}, url = {https://aclanthology.org/2006.bcs-1.11/} } ``` - [← previous The BLARK concept and BLARK for Arabic](https://md.research.elamur.ai/free/en/papers/maegaard-2006-blark-concept-blark-arabic/) - [next → Lexicon Acquisition for Dialectal Arabic Using Transductive Learning](https://md.research.elamur.ai/free/en/papers/duh-2006-lexicon-acquisition-dialectal-arabic-transductive/) - [↑ back to papers of 2006](https://md.research.elamur.ai/free/en/papers/2006/page/2/) ## References 13 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Al-Munjid Dictionary (2002). 39 th edition. Beirut: Dar Al-Mashreq. [find](https://scholar.google.com/scholar?q=Al%2DMunjid+Dictionary+%282002%29%2E+39+th+edition%2E+Beirut%3A+Dar+Al%2DMashreq%2E) 2. Al-Qamoos Al-Muheet Dictionary (1994). 4 th edition. Beirut: Mu'asasat Al-Risalah. [find](https://scholar.google.com/scholar?q=Al%2DQamoos+Al%2DMuheet+Dictionary+%281994%29%2E+4+th+edition%2E+Beirut%3A+Mu%27asasat+Al%2DRisalah%2E) 3. Al-Salman, Saleh (2004). The Effectiveness of Machine Translation. In IJAIS, International Journal of Arabic-English Studies, 5, 145-160. [↗](https://doi.org/10.33806/ijaes2000.5.1.8) 4. Alsharaf, Haitham, S. Cardy, P. Greenfield, and Y. Shen (2004). Problems and Solutions in Machine Translation Involving Arabic, Chinese and French. In Proceedings of the International Conference on Information Technology: Coding and Computing (ITTC04). No page numbers. [find](https://scholar.google.com/scholar?q=Alsharaf%2C+Haitham%2C+S%2E+Cardy%2C+P%2E+Greenfield%2C+and+Y%2E+Shen+%282004%29%2E+Problems+and+Solutions+in+Machine+Translation+Involving+Arabic%2C+Chinese+and+French%2E+In+Proceedings+of+the+International+Conference+on+In) 5. Al-Waseet Dictionary (1972). 2 nd edition. Istanbul: Islamic Library. [find](https://scholar.google.com/scholar?q=Al%2DWaseet+Dictionary+%281972%29%2E+2+nd+edition%2E+Istanbul%3A+Islamic+Library%2E) 6. Al-Wasiti, Salman (2005). al-tafaa C ul bayna al-?insaan wa al-?aalah (interaction between humans and machines). Downloaded from \ on 25 August 2006. [find](https://scholar.google.com/scholar?q=Al%2DWasiti%2C+Salman+%282005%29%2E+al%2Dtafaa+C+ul+bayna+al%2D%3Finsaan+wa+al%2D%3Faalah+%28interaction+between+humans+and+machines%29%2E+Downloaded+from+%3Cwww%2Ealmughtarib%2Ecom%3E+on+25+August+2006%2E) 7. Chalabi, Achraf (2001). Sakhr Web-based Arabic/English MT Engine. Downloaded from \ on 25 August 2006. [find](https://scholar.google.com/scholar?q=Chalabi%2C+Achraf+%282001%29%2E+Sakhr+Web%2Dbased+Arabic%2FEnglish+MT+Engine%2E+Downloaded+from+%3Cwww%2Eelsnet%2Eorg%2Farabic2001%2Fchalabi%2Epdf%3E+on+25+August+2006%2E) 8. Farghaly, Ali and Jean Senellart (2003). Intuitive Coding of the Arabic Lexicon. A paper read at The MT Summit IX - Workshop: Machine translation for semitic languages, New Orleans, USA, 23 September 2003. Downloaded from \<[http://webspace.isi.edu/mt-archive/languages-1.htm](http://webspace.isi.edu/mt-archive/languages-1.htm)> [↗](http://webspace.isi.edu/mt-archive/languages-1.htm) 9. Gaspari, Federico (2004). Integrating on-line MT services into monolingual web-sites for dissemination purposes: An evaluation perspective'. In Proceedings of the 9th EAMT Workshop: Broadening horizons of machine translation and its applications. Valletta, Malta. 62-72. [find](https://scholar.google.com/scholar?q=Gaspari%2C+Federico+%282004%29%2E+Integrating+on%2Dline+MT+services+into+monolingual+web%2Dsites+for+dissemination+purposes%3A+An+evaluation+perspective%27%2E+In+Proceedings+of+the+9th+EAMT+Workshop%3A+Broadening+horizon) 10. Google On-line Translation Page. \<[http://www.google.ae/language_tools?hl=en](http://www.google.ae/language_tools?hl=en)> visited June-August 2006. [↗](http://www.google.ae/language_tools?hl=en) 11. Lisan Al-Arab Dictionary (1999). 3 rd edition. Bierut: Dar Ihyaa Al-Turath Al-Arabi. [find](https://scholar.google.com/scholar?q=Lisan+Al%2DArab+Dictionary+%281999%29%2E+3+rd+edition%2E+Bierut%3A+Dar+Ihyaa+Al%2DTurath+Al%2DArabi%2E) 12. Sakhr's Online Translation Website, Tarjim. \ visited June-August 2006. [find](https://scholar.google.com/scholar?q=Sakhr%27s+Online+Translation+Website%2C+Tarjim%2E+%3Cwww%2Etarjim%2Ecom%3E+visited+June%2DAugust+2006%2E) 13. Systran On-line Translation Website. \ visited June-August 2006. [find](https://scholar.google.com/scholar?q=Systran+On%2Dline+Translation+Website%2E+%3Cwww%2Esystranet%2Ecom%3E+visited+June%2DAugust+2006%2E) *Updated 1 November 2026*