We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The key hypothesis of multilingual learning is that by combining cues from multi...
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, ...
We describe a new tagging model where the states of a hidden Markov model (HMM) estimated by unsupervised learning are incorporated as the features in a maximum entropy model. Our...
It is known that POS tagging is not very accurate for unknown words (words which the POS tagger has not seen in the training corpora). Thus, a first step to improve the tagging ac...
Dan Tufis, Elena Irimia, Radu Ion, Alexandru Ceaus...
This paper proposes a new unsupervised learning method for obtaining English part-ofspecch(POS) disambiguation rules which would improve thc accuracy of a POS tagger. This method ...
We propose a new model for unsupervised POS tagging based on linguistic distinctions between open and closed-class items. Exploiting notions from current linguistic theory, the sy...