The Discovery of Spoken Language marks one of the first efforts to integrate the field of infant speech perception research into the general study of language acquisition. It fills in a key part of the acquisition story by providing an extensive review of research on the acquisition of language during the first year of life, focusing primarily on how normally developing infants learn the organization of native language sound patterns.
Symbolic and statistical approaches to language have historically been at odds—the former viewed as difficult to test and therefore perhaps impossible to define, and the latter as descriptive but possibly inadequate. At the heart of the debate are fundamental questions concerning the nature of language, the role of data in building a model or theory, and the impact of the competence-performance distinction on the field of computational linguistics. Currently, there is an increasing realization in both camps that the two approaches have something to offer in achieving common goals.
Construal presents a new theory of sentence processing, one that allows a limited type of underspecification in the syntactic analysis of sentences. It extends what has arguably been the dominant theory of parsing (the garden-path theory developed by Lyn Frazier and colleagues) through the 1980s into new and previously unexplored domains, and greatly advances the potential for insights into how meaning is both made and understood.
Eugene Charniak breaks new ground in artificial intelligence research by presenting statistical language processing from an artificial intelligence point of view in a text for researchers and scientists with a traditional computer science background.