More Like this

1. ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence

   Alsarra, Sultan; Abdeljaber, Luay; Yang, Wooseong; Zawad, Niamat; Khan, Latifur; Brandt, Patrick; Osorio, Javier; D'Orazio, Vito (July 2023, Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing https://aclanthology.org/2023.ranlp-1.11)

   Mitkov, Ruslan; Angelova, Galia (Ed.)

   This study investigates the use of Natural Language Processing (NLP) methods to analyze politics, conflicts and violence in the Middle East using domain-specific pre-trained language models. We introduce Arabic text and present ConfliBERT-Arabic, a pre-trained language models that can efficiently analyze political, conflict and violence-related texts. Our technique hones a pre-trained model using a corpus of Arabic texts about regional politics and conflicts. Performance of our models is compared to baseline BERT models. Our findings show that the performance of NLP models for Middle Eastern politics and conflict analysis are enhanced by the use of domain-specific pre-trained local language models. This study offers political and conflict analysts, including policymakers, scholars, and practitioners new approaches and tools for deciphering the intricate dynamics of local politics and conflicts directly in Arabic. 

   more » « less
2. Learning Intonation Pattern Embeddings for Arabic Dialect Identification

   https://doi.org/10.21437/interspeech.2020-2906  

   Alvarez, Aitor Arronte; Issa, Elsayed Sabry (October 2020, INTERSPEECH 2020)

   null (Ed.)
3. Noisy-Channel Processing in Standard Arabic Relative Clauses

   Dodd, N; Boush, F; Leung, T; Ferreira, F; Morgan, E (July 2024, Proceedings of the Annual Meeting of the Cognitive Science Society)

   This study investigates sentence processing in Standard Arabic (SA) by examining subject- and object-extracted relative clauses (SRCs and ORCs) through eye tracking. We test memory- and expectation-based theories of processing difficulty, and whether good-enough or noisy-channel processing leads to misinterpretations in ORCs. Our results find increased processing difficulty in ORCs, supporting expectation-based theories; however, this processing difficulty is not localized to the disambiguating region (relative clause verb) as predicted, but rather at the integration of the second noun phrase (relative clause NP). The findings support goodenough/noisy-channel processing theories, suggesting that readers may accept a noisy SRC interpretation of an ORC, and thus bypass integration costs at the RC NP. 

   more » « less
4. Noisy-Channel Processing in Standard Arabic Relative Clauses

   Dodd, N; Boush, F; Leung, T; Ferreira, F; Morgan, E (July 2024, Proceedings of the Annual Meeting of the Cognitive Science Society)

   This study investigates sentence processing in Standard Arabic (SA) by examining subject- and object-extracted relative clauses (SRCs and ORCs) through eye tracking. We test memory- and expectation-based theories of processing difficulty, and whether good-enough or noisy-channel processing leads to misinterpretations in ORCs. Our results find increased processing difficulty in ORCs, supporting expectation-based theories; however, this processing difficulty is not localized to the disambiguating region (relative clause verb) as predicted, but rather at the integration of the second noun phrase (relative clause NP). The findings support goodenough/noisy-channel processing theories, suggesting that readers may accept a noisy SRC interpretation of an ORC, and thus bypass integration costs at the RC NP. 

   more » « less
5. PALI: A Language Identification Benchmark for Perso-Arabic Scripts

   https://doi.org/10.18653/v1/2023.vardial-1.8  

   Ahmadi, Sina; Agarwal, Milind; Anastasopoulos, Antonios (January 2023, Association for Computational Linguistics)