The edge weights between the foreign language trigrams are computed using a co-occurence based similarity function, designed to indicate how syntactically

They considered a semi-supervised POS tagging scenario and showed that one can use a graph over trigram types, and edge weights based on distributional similarity, to improve a supervised conditional random field tagger.

We use two different similarity functions to define the edge weights among the foreign vertices and between vertices from different languages.

Table 1: Various features used for computing edge weights between foreign trigram types.

However, the original TPR ignores the topic context when setting the edge weights; the edge weight is set by counting the number of co-occurrences of the two words within a certain window size.

Taking the topic of “electronic products” as an example, the word “juice” may co-occur frequently with a good keyword “apple” for this topic because of Apple electronic products, so “juice” may be ranked high by this context-free co-occurrence edge weight although it is not related to electronic products.

jiwj—WM (2) Here we compute the propagation from wj to w,- in the context of topic 75, namely, the edge weight from wj to w,- is parameterized by t. In this paper, we compute edge weight 6,; (wj, between two words by counting the number of co-occurrences of these two words in tweets assigned to topic 75.