This study compares the syllable structures of nine Arabic varieties from Wiktionary, using a computational syllabifier. It further investigates methods for learning syllable boundaries in unsyllabified words transcribed in the International Phonetic Alphabet (IPA). The syllabification algorithm is evaluated under three conditions: (i) Default, employing fixed rules; (ii) Joint, learning onsets and codas across all varieties collectively; and (iii) Per-variety, learning onsets and codas specific to each variety. Results indicate that the default configuration yields the highest accuracy, ranging from 97.05% to 100%. The per-variety approach achieves 90.64% to 100% accuracy, while the joint approach ranges from 84.63% to 94.74%. A cross-variety analysis using Jensen-Shannon divergence reveals three principal groupings: Egyptian, Hejazi, and Modern Standard Arabic are closely related; Levantine and Gulf varieties constitute a second cluster; and Juba Arabic, Maltese, and Moroccan emerge as outliers. A cleaned dataset encompassing all nine varieties is also provided.

We present a new database of Romance clitics across nine varieties. The database includes speech, transcriptions, and linguistic annotations. The database concentrates on clitics, and includes varieties of Romance with stressed clitics. Specifically, the database includes data from the regions of Corsica, Pyrénées-Atlantiques, Sardinia, Liguria, Basilicata, Campania, Mallorca, Menorca, and Formentera. A publicly accessible interface allows easy searching. The database and, separately, the interface code will be made publicly available.

We predict lexical stress in Arabic varieties using syllable structure (a sequence of CVs, with C for consonants and V for vowels). Our task is generation: given an unstressed input, the system outputs a stress-marked word. We compare four approaches: a grammar induction algorithm (BUFIA), a transformer-based neural network (NN), a rule-based method, and a frequency baseline. The models are evaluated across several low-resource settings by varying the training data size by words, structural type, and syllable count. BUFIA outperforms the neural network, especially when data are scarce. This supports grammar induction as an interpretable and sample-efficient alternative for learning stress.

We present AraBabyTalk-EGY, an enriched release of the Egyptian Arabic CHILDES corpus, that opens the child-adult interactions genre to modern Arabic NLP research. Starting from the original CHILDES recordings and IPA transcriptions of caregiver-child sessions, we (i) map each IPA token to fully diacritized Arabic script, and (ii) add core part-of-speech tags and lemmas aligned with existing dialectal Arabic morphological resources. These layers yield ~26K annotated tokens suitable for both text- and speech-based NLP tasks. We provide a benchmark on morphological disambiguation and Arabic ASR. We outline lexical and morphosyntactic differences between AraBabyTalk-EGY and general Egyptian Arabic resources, highlighting the value of genre-specific training data for language acquisition studies and Arabic speech technology.

We investigate learning surface forms from underlying morphological forms for low-resource language varieties. We concentrate on learning explicit rules with the aid of learned syllable structure constraints, which outperforms neural methods on this small data task and provides interpretable output. Evaluating across one relatively high-resource and two related low-resource Arabic dialects, we find that a model trained only on the high-resource dialect achieves decent performance on the low-resource dialects, useful when no low-resource training data is available. The best results are obtained when our system is trained only on the low-resource dialect data without augmentation from the related higher-resource dialect. We discuss the impact of syllable structure constraints and the strengths and weaknesses of data augmentation and transfer learning from a related dialect.

Learning morphophonological mappings between the spoken form of a language and its underlying morphological structures is crucial for enriching resources for morphologically rich languages like Arabic. In this work, we focus on Egyptian Arabic as our case study and explore the integration of linguistic knowledge with a neural transformer model. Our approach involves learning to correct the residual errors from hand-crafted rules to predict the spoken form from a given underlying morphological representation. We demonstrate that using a minimal set of rules, we can effectively recover errors even in very low-resource settings.

We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method relies on comparing the reconstruction probabilities of tokens in a given sequence when conditioned on the representation of a single token that has been fully contextualized and when conditioned on only the decontextualized lexical prior of the model. This comparison can be understood as quantifying the contribution of contextualization towards reconstruction—the difference in the reconstruction probabilities can only be attributed to the representational change of the single token induced by contextualization. We apply this analysis to three MLMs and find that contextualization boosts reconstructability of tokens that are close to the token being reconstructed in terms of linear and syntactic distance. Furthermore, we extend our analysis to finer-grained decomposition of contextualized representations, and we find that these boosts are largely attributable to static and positional embeddings at the input layer.

This paper presents a novel approach to the Arabic Reverse Dictionary Shared Task at WANLP 2023 by leveraging the BERT Multilingual model and introducing modifications augmentation and using a multi attention head. The proposed method aims to enhance the performance of the model in understanding and generating word embeddings for Arabic definitions, both in monolingual and cross-lingual contexts. It achieved good results compared to benchmark and other models in the shared task 1 and 2.

This paper presents the 259 team’s BERT ensemble designed for the NADI 2022 Subtask 2 (sentiment analysis) (Abdul-Mageed et al., 2022). Twitter Sentiment analysis is one of the language processing (NLP) tasks that provides a method to understand the perception and emotions of the public around specific topics. The most common research approach focuses on obtaining the tweet’s sentiment by analyzing its lexical and syntactic features. We used multiple pretrained Arabic-Bert models with a simple average ensembling and then chose the best-performing ensemble on the training dataset and ran it on the development dataset. This system ranked 3rd in Subtask 2 with a Macro-PN-F1-score of 72.49%.

In this paper, we present the results and findings of the Shared Task on Gender Rewriting, which was organized as part of the Seventh Arabic Natural Language Processing Workshop. The task of gender rewriting refers to generating alternatives of a given sentence to match different target user gender contexts (e.g., a female speaker with a male listener, a male speaker with a male listener, etc.). This requires changing the grammatical gender (masculine or feminine) of certain words referring to the users. In this task, we focus on Arabic, a gender-marking morphologically rich language. A total of five teams from four countries participated in the shared task.