Noise-Robust Morphological Disambiguation for Dialectal Arabic

Proceedings of NAACL-HLT 2018, pages 953–964 New Orleans, Louisiana, June 1 - 6, 2018. c⃝2018 Association for Computational Linguistics Noise-Robust Morphological Disambiguation for Dialectal Arabic Nasser Zalmout, Alexander Erdmann, Nizar Habash Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates {nasser.zalmout,ae1541,nizar.habash}@nyu.edu Abstract User-generated text tends to be noisy with many lexical and orthographic inconsistencies, making natural language processing (NLP) tasks more challenging. The challenging na- ture of noisy text processing is exacerbated for dialectal content, where in addition to spelling and lexical differences, dialectal text is char- acterized with morpho-syntactic and phonetic variations. These issues increase sparsity in NLP models and reduce accuracy. We present a neural morphological tagging and disam- biguation model for Egyptian Arabic, with various extensions to handle noisy and incon- sistent content. Our models achieve about 5% relative error reduction (1.1% absolute im- provement) for full morphological analysis, and around 22% relative error reduction (1.8% absolute improvement) for part-of-speech tag- ging, over a state-of-the-art baseline. 1 Introduction There has been a growing interest in noise-robust NLP tools recently, motivated by the sheer mag- nitude of user-generated content in social media platforms. The noisy nature of user-generated content makes its processing very challenging for NLP tools. Noisy content is non-canonical in na- ture, with lexical, orthographic, and phonetic vari- ations that increase the perplexity and sparsity of NLP models. Several contributions show consid- erable drop in performance for a number of tasks, where simply retraining existing models with so- cial media data does not provide substantial im- provement (Gimpel et al., 2011; Ritter et al., 2011; Habash et al., 2013a). Morphological disambiguation for noisy con- tent is further complicated for dialectal content, with additional morpho-syntactic variations. Mor- phological disambiguation is also more challeng- ing for morphologically rich and ambiguous lan- guages, like Arabic and Dialectal Arabic (DA). Arabic is morphologically rich, having more fully inflected words (types) than morphologically poorer languages. It is also ambiguous, with short vowels (diacritic marks) often dropped and disam- biguated in context. These issues result in more morpho-syntactic variations for DA in written text compared to other dialectal content, and increase the number of potential analyses. We present several morphological disambigua- tion models for Egyptian Arabic (EGY), based on previous models for EGY and Modern Standard Arabic (MSA). We use a bidirectional long short term memory (Bi-LSTM) architecture and vari- ous noise reduction techniques, including char- acter embedding and embedding space mapping. We also experiment with the width of the embed- ding window in the pre-trained embeddings. Char- acter embeddings allow access to subword units, while the embedding space mapping normalizes non-canonical forms to canonical neighbors. The narrow/wide embedding window in the pre-trained embeddings allows for more of syntactic/semantic modeling, respectively. The goal of the various models is to achieve noise-robust analysis, rather than explicit noise normalization. We therefore use the normaliza- tion techniques on the vector-level only, instead of replacing the raw forms, which allows for less aggressive lexical normalization. The separation of raw forms and …

Content truncated to 500 words