This dissertation is a study of negative concord in Levantine Arabic (Israel/Palestine, Jordan, Lebanon, Syria), where negative concord is defined as the failure of an n-word to express negative meaning distinctly when in syntagm with another negative expression. A set of n-words is identified, including the "never-words" ʔɛbadan (Arabic أبداً) and bɪlmarra (Arabic بالمرّة) “never, not once, not at all,” the negative minimizers hawa (Arabic هوا) and qɛšal (Arabic قشل) “nothing,” and the negative scalar focus particle wala (Arabic ولا) “not (even) (one), not a (single).” Each can be used to express negation in sentence fragments and other constructions with elliptical interpretations, such as gapping and sub-sentential constituent coordination. Beyond that, the three categories differ syntactically and semantically. I present analyses of these expressions that treat them as having different morphological and semantic properties. The data support an ambiguity analysis for wala-phrases, and a syntactic analysis of it with never-words, indicating that a single, uniform theory of negative concord should be rejected for Levantine Arabic.

The dissertation is the first such work to explicitly identify negative concord in Levantine Arabic, and to provide a detailed survey and analysis of it. The description includes subtle points of variation between regional varieties of Levantine, as well as in depth analysis of the usage of n-words. It also adds a large new data set to the body of data that has been reported on negative concord, and have several implications for theories on the subject. The dissertation also makes a contribution to computational linguistics as applied to Arabic, because the analyses are couched in Combinatory Categorial Grammar, a formalism that is used both for linguistic theorizing as well as for a variety of practical applications, including text parsing and text generaration. The semantic generalizations reported here are also important for practical computational tasks, because they provide a way to correctly calculate the negative or positive polarity of utterances in a negative concord language, which is essential for computational tasks such as machine translation or sentiment analysis.