This paper presents an effective method for generating natural language sentences from their underlying meaning representations. The method is built on top of a hybrid tree repres...
We extend previous work on fully unsupervised part-of-speech tagging. Using a non-parametric version of the HMM, called the infinite HMM (iHMM), we address the problem of choosing...
Jurgen Van Gael, Andreas Vlachos, Zoubin Ghahraman...
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
In this paper, we propose a linear model-based general framework to combine k-best parse outputs from multiple parsers. The proposed framework leverages on the strengths of previo...
Most existing information retrieval (IR) systems do not take much advantage of natural language processing (NLP) techniques due to the complexity and limited observed effectivenes...