---
title: "Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge — Naser 2018"
description: "This paper covers the Birzeit University entry to the Arabic Dialect Identification (ADI) task at VarDial… 61.3% F1. 8 references, cited by 1 paper here."
authors: ["Rabee Naser", "Abualsoud Hanani"]
year: 2018
venue: "Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)"
source: "https://aclanthology.org/W18-3924/"
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/naser-2018-birzeit-arabic-dialect-identification-system/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/naser-2018-birzeit-arabic-dialect-identification-system/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/5/) / Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge

# Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge

**Authors:** Rabee Naser and Abualsoud Hanani · **Year:** 2018 · **Venue:** Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W18-3924/) · [PDF](https://aclanthology.org/W18-3924.pdf) · [OpenAlex](https://openalex.org/W2911976377)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 140,884 papers whose bibliographies we read

## Summary
This paper covers the Birzeit University entry to the Arabic Dialect Identification (ADI) task at VarDial 2018. The task is to label broadcast speech as Egyptian, Gulf, Levantine, North African or MSA. Organizers supplied 600-dimensional acoustic embeddings, Arabic ASR word transcripts, phone strings from four non-Arabic recognizers and the WAV audio. The test set was much larger than in 2017 and partly drawn from YouTube, so it differed from the training conditions.

The officially submitted run used majority voting over SVM and feed-forward networks trained on the embeddings. It placed third with 53.38%. After the deadline the authors built many more systems:
- GMM-UBM and GMM tokenizer models on MFCC features
- word and phoneme TF-IDF with SVM
- PRLM
- a Jaccard similarity-to-every-training-sentence representation

Compressing the embedding and similarity views through 30-neuron bottleneck layers reached 61.3% F1 macro. This exceeds every official score. An SVM fusion, trained with cross-validation on the test outputs, reached 68.77% F1 micro. The paper shows that cheap lexical views and acoustic views are strongly complementary.

## Key points
- **Data:** 14,591 train, 1,566 dev and 6,837 test utterances. 5,435 test items were added to the original 1,492 from MGB-3, so the test set was about 4.5 times the 2017 size.
- **Official result:** the voting run of embedding-based SVM and DNN models ranked 3rd of six teams (0.5338). UnibucKernel was 1st (0.5892).
- **Single-system scores (post-deadline):**

  | System | Score |
  |---|---|
  | GMM-UBM (2048 mixtures) | 35.1% |
  | GMM tokenizer (best) | 47.86% |
  | Word TF-IDF (68,707-word vocabulary) + SVM | 51.47% |
  | Jaccard sentence similarity (16,157 features) + SVM | 51.89% |
  | Czech PRLM on dev (best) | 38.9% |
  | Phoneme TF-IDF on dev | 41.12% |

- **Bottleneck system:** two 30-neuron bottleneck layers were concatenated into a 60-dimensional vector and fed to an SVM. It scored 61.3% F1 macro, about 2.5 points above the official winner.
- **Fusion:** SVM fusion of 5-score output vectors, using 7-fold cross-validation over the test data, gave 68.77% F1 micro. Because the fusion was fit on test-set outputs, this number is not directly comparable to the official results.

## Interesting ideas
- Represent each item by its overlap similarity to every labelled example and let a classifier learn from that profile; this exemplar view beat a much larger TF-IDF vector while needing no linguistic features.
- Before fusing, check how often two systems are right on the same items versus only one of them (here 30% vs. 40%), since low overlap is what justifies combining them.
- Squeeze two very high-dimensional, heterogeneous views through small bottleneck layers and concatenate the compact codes, so neither view drowns the other in the final classifier.
- Turn a continuous signal into discrete symbols by taking the most likely mixture component per frame, then model the resulting token n-grams like phones.
- Fitting fusion weights by cross-validation on the test outputs inflates results, and a new recording domain clearly lowered every system's score.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): we could profile new silver sentences by their Jaccard similarity to agreed training sentences, flagging ones with no close neighbours as out-of-distribution before trusting them.
- **I2** (learn): compute this overlap between witness parsers per relation type to decide which witnesses actually add information to silver agreement.
- **I3** (tree): gparse could merge lexical and contextual feature blocks via small learned bottlenecks, keeping each block's contribution inspectable as a separate short vector.
- **I4** (tokens): continuous embedding states could be quantized into a small symbol inventory, giving the tagger discrete, countable morphology-like units it can explain.
- **I5** (learn): keep combination weights tuned only on held-out dev data and add a deliberately out-of-domain negative-control set to expose such gains.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · [🐪 Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/)

## Institutions

- [Birzeit University](https://md.research.elamur.ai/free/en/universities/birzeit-university/) — University, Birzeit, Palestine · 10 works · 249 citations

## Cite

Cite as: Rabee Naser and Abualsoud Hanani. 2018. Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge. Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{naser2018birzeit,
  title = {{Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge}},
  author = {Rabee Naser and Abualsoud Hanani},
  booktitle = {Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)},
  year = {2018},
  url = {https://aclanthology.org/W18-3924/}
}
```

- [← previous The WAW Corpus: The First Corpus of Interpreted Speeches and their Translations for English and Arabic](https://md.research.elamur.ai/free/en/papers/abdelali-2018-waw-corpus-first-corpus-interpreted/)
- [next → Classifier Ensembles for Dialect and Language Variety Identification](https://md.research.elamur.ai/free/en/papers/dinu-2018-classifier-ensembles-dialect-language-variety/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/5/)

## References

8 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 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. In Proceedings of INTERSPEECH, pages 2934–2938. [find](https://scholar.google.com/scholar?q=Ahmed+Ali%2C+Najim+Dehak%2C+Patrick+Cardinal%2C+Sameer+Khurana%2C+Sree+Harsha+Yella%2C+James+Glass%2C+Peter+Bell%2C+and+Steve+Renals%2E+2016%2E+Automatic+Dialect+Detection+in+Arabic+Broadcast+Speech%2E+In+Proceedings+of+)
2. Andrea DeMarco and Stephen J. COX. 2013. Native accent classification via i-vectors and speaker compensation fusion. In Proceedings of INTERSPEECH, pages 1472–1476. [find](https://scholar.google.com/scholar?q=Andrea+DeMarco+and+Stephen+J%2E+COX%2E+2013%2E+Native+accent+classification+via+i%2Dvectors+and+speaker+compensation+fusion%2E+In+Proceedings+of+INTERSPEECH%2C+pages+1472%E2%80%931476%2E)
3. Abualsoud Hanani, Aziz Qaroush, and Stephen Taylor. 2017. Identifying dialects with textual and acoustic cues. In Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), pages 93–101, Valencia, Spain, April. [find](https://scholar.google.com/scholar?q=Abualsoud+Hanani%2C+Aziz+Qaroush%2C+and+Stephen+Taylor%2E+2017%2E+Identifying+dialects+with+textual+and+acoustic+cues%2E+In+Proceedings+of+the+Fourth+Workshop+on+NLP+for+Similar+Languages%2C+Varieties+and+Dialect)
4. Radu Tudor Ionescu and Andrei Butnaru. 2017. Learning to identify arabic and german dialects using multiple kernels. In Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), pages 200–209, Valencia, Spain, April. [find](https://scholar.google.com/scholar?q=Radu+Tudor+Ionescu+and+Andrei+Butnaru%2E+2017%2E+Learning+to+identify+arabic+and+german+dialects+using+multiple+kernels%2E+In+Proceedings+of+the+Fourth+Workshop+on+NLP+for+Similar+Languages%2C+Varieties+and+D)
5. Shervin Malmasi, Marcos Zampieri, Nikola Ljubešić, Preslav Nakov, Ahmed Ali, and Jörg Tiedemann. 2016. Discriminating between similar languages and arabic dialect identification: A report on the third dsl shared task. In Proceedings of the 3rd Workshop on Language Technology for Closely Related Languages, Varieties and Dialects (VarDial), Osaka, Japan. [our card](https://md.research.elamur.ai/free/en/papers/malmasi-2016-discriminating-between-similar-languages/)
6. Maryam Najafian, Sameer Khurana, Suwon Shon, Ahmed Ali, and James Glass. 2018. Exploiting convolutional neural networks for phonotactic based dialect identification. In ICASSP. [find](https://scholar.google.com/scholar?q=Maryam+Najafian%2C+Sameer+Khurana%2C+Suwon+Shon%2C+Ahmed+Ali%2C+and+James+Glass%2E+2018%2E+Exploiting+convolutional+neural+networks+for+phonotactic+based+dialect+identification%2E+In+ICASSP%2E)
7. Marcos Zampieri, Shervin Malmasi, Nikola Ljubešić, Preslav Nakov, Ahmed Ali, Jörg Tiedemann, Yves Scherrer, and Noëmi Aepli. 2017. Findings of the VarDial Evaluation Campaign 2017. In Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), Valencia, Spain. [our card](https://md.research.elamur.ai/free/en/papers/zampieri-2017-findings-vardial-evaluation-campaign/)
8. Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Ahmed Ali, Suwon Shuon, James Glass, Yves Scherrer, Tanja Samardžić, Nikola Ljubešić, Jörg Tiedemann, Chris van der Lee, Stefan Grondelaers, Nelleke Oostdijk, Antal van den Bosch, Ritesh Kumar, Bornini Lahiri, and Mayank Jain. 2018. Language Identification and Morphosyntactic Tagging: The Second VarDial Evaluation Campaign. In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), Santa Fe, USA. [our card](https://md.research.elamur.ai/free/en/papers/zampieri-2018-language-identification-morphosyntactic-tagging-second/)