Many contemporary language technology systems are characterized by long pipelines of tools with complex dependencies. Too often, these workflows are implemented by ad hoc scripts;...
We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...
We describe a pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus. Th...
Zach Solan, David Horn, Eytan Ruppin, Shimon Edelm...
We have been developing a spoken language system to recognize and understand spontaneous speech. It is difficult for such systems to achieve good coverage of the lexicon and gramm...
Synchronous languages rely on formal methods to ease the development of applications in an efficient and reusable way. Formal methods have been advocated as a means of increasing t...