Averaged Perceptron

This paper presents a comparative study of five parameter estimation algorithms on four NLP tasks. Three of the five algorithms are well-known in the computational linguistics community: Maximum Entropy (ME) …...

We describe a discriminatively trained se- quence alignment model based on the av- eraged perceptron. In common with other approaches to sequence modeling using per- ceptrons, and in contrast with …...

We describe our experiments using the DeSR parser in the multilingual and do- main adaptation tracks of the CoNLL 2007 shared task. DeSR implements an incre- mental deterministic Shift/Reduce parsing …...

This paper shows that discriminative reranking with an averaged perceptron model yields substantial improvements in realization quality with CCG. The paper confirms the utility of including language model log probabilities …...

This paper describes POS tagging exper- iments with semi-supervised training as an extension to the (supervised) averaged perceptron algorithm, first introduced for this task by (Collins, 2002). Experiments with an …...