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...
Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multistrategy and multi-source approach to question...
Jennifer Chu-Carroll, Krzysztof Czuba, John M. Pra...
In this paper, the automatic labeling of semantic roles in a sentence is considered as a chunking task. We define a semantic chunk as the sequence of words that fills a semantic...
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within...
This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is gener...