State-of-the-art and human ceiling for part-of-speech tagging is 97%, while the baseline method (Most Frequent Class Baseline) has a comparable results of 92% on the WSJ Corpus (English).

University of Michigan - Ann Arbor

In corpus linguistics, part-of-speech tagging (POS tagging or PoS tagging or POST), also called grammatical tagging is the process of marking up a word in a text (corpus) as corresponding to a particular part of speech, based on both its definition and its context. A simplified form of this is commonly taught to school-age children, in the identification of words as nouns, verbs, adjectives, adverbs, etc. 

Part-of-speech Tagging

Research papers, articles and examples about POS Tagging in NLP

Part-of-speech Tagging References

Decoding, in models such as HMM that contains hidden variables, is the task that takes as input an HMM $\lambda = (A, B)$ and a sequence of observations $O = o_1 , ..., o_T$, and finds the most probable sequence of states $Q = q_1...q_T$. 

For part-of-speech tagging, the goal of HMM decoding is to choose the tag sequence $t_1...t_n$ that is most probable given the observation sequence of n words $w_1...w_n$:
$$\hat t_{1:n} = \argmax_{t_1, ..., t_n} P(t_1...t_n|w_1...w_n)$$



HMM Tagging as Decoding

Accuracy of Part-of-speech Tagging

Given an ambiguous word, choose the part-of-speech (POS) tag which is most frequent in the training corpus. Thus, a POS Classifier's performance can be compared with this baseline method.

Most Frequent Class Baseline

14%-15% of the vocabulary are words with 2 or more part-of-speech tags, while in running text (word tokens), 55-67% are words are ambiguous.

Words with Ambiguous Part-of-speech

For an input sequence of words [x1, x2, ... xn], each item is assigned its part-of-speech correctly. This is a disambiguation task as one word can have more than one potential part-of-speech.

Learn Before

Related