--- title: "Arabic Dialect Identification Using iVectors and ASR Transcripts" description: "The paper describes the systems that the MAZA team submitted to VarDial 2017's… 71.7% accuracy. 3 references, cited by 22 papers here." authors: ["Shervin Malmasi", "Marcos Zampieri"] year: 2017 venue: "Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)" source: "https://aclanthology.org/W17-1222/" doi: "10.18653/v1/w17-1222" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/malmasi-2017-arabic-dialect-identification-ivectors-asr/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/malmasi-2017-arabic-dialect-identification-ivectors-asr/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/4/) / Arabic Dialect Identification Using iVectors and ASR Transcripts # Arabic Dialect Identification Using iVectors and ASR Transcripts **Authors:** [Shervin Malmasi](https://md.research.elamur.ai/free/en/authors/shervin-malmasi/) and [Marcos Zampieri](https://md.research.elamur.ai/free/en/authors/marcos-zampieri/) · **Year:** 2017 · **Venue:** [Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)](https://md.research.elamur.ai/free/en/venues/vardial/) ([VarDial 2017](https://md.research.elamur.ai/free/en/venues/vardial/2017/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/W17-1222/) · [PDF](https://aclanthology.org/W17-1222.pdf) · [DOI 10.18653/v1/w17-1222](https://doi.org/10.18653/v1/w17-1222) · [OpenAlex](https://openalex.org/W2740300618) **Citations:** 31 citations (OpenAlex, 2026-10-14) · [22](https://md.research.elamur.ai/free/en/papers/malmasi-2017-arabic-dialect-identification-ivectors-asr/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper describes the systems that the MAZA team submitted to VarDial 2017's shared task on Arabic Dialect Identification (ADI). The task was to label Arabic utterances as Modern Standard Arabic (MSA) or one of four dialects: Egyptian, Gulf, Levantine or North-African. It was the first ADI edition to provide both acoustic data and ASR transcripts. The data are Al Jazeera broadcast, debate and discussion recordings from the dataset of Ali et al. (2016). The authors trained one linear SVM per feature type: - word unigrams, - character n-grams of length 1–8, taken from raw transcripts with no preprocessing, - the supplied iVector audio features. They then combined these classifiers in three ways: plain voting, averaging of Platt-scaled probabilities, and a stacked Random Forest meta-classifier. In cross-validation the audio iVectors were clearly the strongest single feature, and every combination beat every individual classifier. On the test set the meta-classifier was best, reaching about 71.7% accuracy and placing second of six teams. The work shows that mixing speech-derived and text-derived evidence pays off for telling apart closely related varieties. ## Key points - **Data:** 25,311 train/dev samples were merged for training, and the test set had 1,492 instances. The test majority-class baseline was 23.1%. - **Single features in cross-validation:** iVectors scored 85.3%, while the best transcript feature (character 6-grams) scored 76.2%. Character 4-grams and longer outperformed word unigrams. - **Ensembles in cross-validation:** voting reached 85.4%, mean probability 95.0% and the meta-classifier 97.7%. In the voting system, 1,165 samples (4.60%) ended in ties that were broken arbitrarily. - **Test results:** | System | Accuracy | Weighted F1 | |---|---|---| | Run 1 (voting) | 0.6086 | 0.6073 | | Run 2 (mean probability) | 0.6689 | 0.6679 | | Run 3 (meta-classifier) | 0.7165 | 0.7170 | Teams were ranked by weighted F1. - **Errors by class:** MSA was recognised much more reliably than any dialect. Gulf and Levantine were the pair most often confused. ## Interesting ideas - Averaging class probabilities lets a classifier contribute support for the right label even when that label is only its second choice, which makes this combiner more robust than hard voting. - Stacking trains a second-level model, here a Random Forest, on the base classifiers' outputs via cross-validation, so it learns which witness to trust in which situation. - With an even number of voters, ties are common (4.6% of training samples here) and were resolved arbitrarily, which silently adds noise. - Cross-validation accuracy of 97.7% fell to 71.7% on held-out test data, a warning that in-sample stacking estimates can be badly optimistic. - Character n-grams taken directly from unnormalised text capture sub-word cues such as affixes and syllables without needing a tokenizer. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (learn): when several witness parsers vote on silver arcs, combining their scored alternatives instead of single top picks could recover agreement that hard votes miss. - **I2** (learn): a small explainable meta-model over parser confidences could decide when silver data is trustworthy, while still exposing which parser drove each decision. - **I3** (learn): silver-agreement pipelines should count ties explicitly and route them to an LLM teacher tier rather than breaking them at random. - **I4** (learn): evaluations of combined systems should always include a truly unseen split and negative controls, not just cross-validation on training material. - **I5** (tokens): character-level evidence could back up the tagger and lemmatizer on unknown or noisy words, while staying an inspectable feature. *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 - [Harvard University](https://md.research.elamur.ai/free/en/universities/harvard-university/) — University, Cambridge, United States · 126 works · 45,130 citations - [Macquarie University](https://md.research.elamur.ai/free/en/universities/macquarie-university/) — University, Sydney, Australia · 44 works · 5,778 citations - [University of Cologne](https://md.research.elamur.ai/free/en/universities/university-of-cologne/) — University, Cologne, Germany · 9 works · 407 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works 🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works · [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 519 works ## Cite Cite as: Shervin Malmasi and Marcos Zampieri. 2017. Arabic Dialect Identification Using iVectors and ASR Transcripts. Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{malmasi2017arabic, title = {{Arabic Dialect Identification Using iVectors and ASR Transcripts}}, author = {Shervin Malmasi and Marcos Zampieri}, booktitle = {Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)}, year = {2017}, doi = {10.18653/v1/w17-1222}, url = {https://doi.org/10.18653/v1/w17-1222} } ``` - [← previous Lexical Features in Coreference Resolution: To be Used With Caution](https://md.research.elamur.ai/free/en/papers/moosavi-2017-lexical-features-coreference-resolution-be/) - [next → Discourse Markers in Speech: Distinctive Features and Corpus Annotation](https://md.research.elamur.ai/free/en/papers/crible-2017-discourse-markers-speech-distinctive-features/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/4/) ## References 3 references, 2 of them with a card of ours. ↗ leads to the work. 1. Rania Al-Sabbagh and Roxana Girju. 2012. [YADAC: Yet another Dialectal Arabic Corpus](https://md.research.elamur.ai/free/en/papers/sabbagh-2012-yadac-yet-another-dialectal-arabic/). In Proceedings of LREC. 2. Ahmed Ali, Najim Dehak, Patrick Cardinal, Sameer Khurana, Sree Harsha Yella, James Glass, Peter Bell, and Steve Renals. 2016. [Automatic Dialect Detection in Arabic Broadcast Speech](https://md.research.elamur.ai/free/en/papers/ali-2015-automatic-dialect-detection-arabic-broadcast/). In Proceedings of INTERSPEECH. 3. Mohamad Hasan Bahari, Najim Dehak, Lukas Burget, Ahmed M Ali, Jim Glass, et al. 2014. Non-negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition. IEEE/ACM transactions on audio, speech, and language processing, 22(7):1117–1129. [↗](https://doi.org/10.1109/taslp.2014.2319159) *Updated 1 November 2026*