Don't throw those morphological analyzers away just yet: Neural morphological disambiguation for Arabic

N Zalmout, N Habash - Proceedings of the 2017 Conference on …, 2017 - aclanthology.org
This paper presents a model for Arabic morphological disambiguation based on Recurrent
Neural Networks (RNN). We train Long Short-Term Memory (LSTM) cells in several …

Adapting word embeddings to new languages with morphological and phonological subword representations

A Chaudhary, C Zhou, L Levin, G Neubig… - arXiv preprint arXiv …, 2018 - arxiv.org
Much work in Natural Language Processing (NLP) has been for resource-rich languages,
making generalization to new, less-resourced languages challenging. We present two …

Adversarial multitask learning for joint multi-feature and multi-dialect morphological modeling

N Zalmout, N Habash - arXiv preprint arXiv:1910.12702, 2019 - arxiv.org
Morphological tagging is challenging for morphologically rich languages due to the large
target space and the need for more training data to minimize model sparsity. Dialectal …

Joint diacritization, lemmatization, normalization, and fine-grained morphological tagging

N Zalmout, N Habash - arXiv preprint arXiv:1910.02267, 2019 - arxiv.org
Semitic languages can be highly ambiguous, having several interpretations of the same
surface forms, and morphologically rich, having many morphemes that realize several …

Morphological analysis and disambiguation for Gulf Arabic: The interplay between resources and methods

S Khalifa, N Zalmout, N Habash - Proceedings of the Twelfth …, 2020 - aclanthology.org
In this paper we present the first full morphological analysis and disambiguation system for
Gulf Arabic. We use an existing state-of-the-art morphological disambiguation system to …

The effect of morphology in named entity recognition with sequence tagging

O Güngör, T Güngör, S Üsküdarli - Natural Language Engineering, 2019 - cambridge.org
This work proposes a sequential tagger for named entity recognition in morphologically rich
languages. Several schemes for representing the morphological analysis of a word in the …

Improving named entity recognition by jointly learning to disambiguate morphological tags

O Güngör, S Üsküdarlı, T Güngör - arXiv preprint arXiv:1807.06683, 2018 - arxiv.org
Previous studies have shown that linguistic features of a word such as possession, genitive
or other grammatical cases can be employed in word representations of a named entity …

Using morphological knowledge in open-vocabulary neural language models

A Matthews, G Neubig, C Dyer - … of the 2018 Conference of the …, 2018 - aclanthology.org
Languages with productive morphology pose problems for language models that generate
words from a fixed vocabulary. Although character-based models allow any possible word …

[PDF][PDF] Joint prediction of morphosyntactic categories for fine-grained Arabic part-of-speech tagging exploiting tag dictionary information

G Inoue - 2019 - naist.repo.nii.ac.jp
Abstract Part-of-speech (POS) tagging for morphologically rich languages such as Arabic is
a challenging problem because of their enormous tag sets. One reason for this is that in the …

[PDF][PDF] Creating lexical resources for polysynthetic languages—The case of Arapaho

G Kazeminejad, A Cowell… - … of the 2nd Workshop on the …, 2017 - aclanthology.org
This paper discusses the challenges in creating pedagogical and research resources for the
Arapaho language. Because of the complex morphology of this language, printed resources …