| Pinyin Input Method Model | The edge weight the negative logarithm of conditional probability P(Sj+1,k SM) that a syllable Sm- is followed by Sj+1,k, which is give by a bigram language model of pinyin syllables: |
| Pinyin Input Method Model | Similar to G8 , the edges are from one syllable to all syllables next to it and edge weights are the conditional probabilities between them. |
| Pinyin Input Method Model | 0 Edges from the start vertex E (210 —> 21351) with edge weight |
| Solution Graph | initial node and edge weights set to 1, edges being created wherever REF or J Prob are not zero). |
| Solution Graph | In the first experiment, referred to as PR1, initial confidence is used as an initial node rank for PR and edge weights are uniform, edges, as in the PR baseline, being created wherever REF or J Prob are not zero. |
| Solution Graph | In our second experiment, PRC, entity coherence features are tested by setting the edge weights to the coherence score and using uniform initial node weights. |
| Keyphrase Extraction Approaches | The edge weight is proportional to the syntactic and/or semantic relevance between the connected candidates. |
| Keyphrase Extraction Approaches | An edge weight in a SW graph denotes the word’s importance in the sentence it appears. |
| Keyphrase Extraction Approaches | Finally, an edge weight in a WW graph denotes the co-occurrence or knowledge-based similarity between the two connected words. |
| Pattern extraction by sentence compression | Edge weight is defined as a linear function over a feature set: ’LU(€) = w - f(e). |
| Pattern extraction by sentence compression | Since we consider compressions with different lengths as candidates, from this set we select the one with the maximum averaged edge weight as the final compression. |
| Pattern extraction by sentence compression | Unlike it, the compression-based method keeps the essential prepositional phrase for divorce in the pattern because the average edge weight is greater for the tree with the prepositional phrase. |
| Extensions | It is straightforward and easy to implement by replacing the row normalized adjacency matrix A with an arbitrary stochastic matrix P. We can use this edge weighted PageRank for CoSimRank. |
| Extensions | We tried a number of different ways of modifying it for weighted graphs: (i) running the random walks with the weighted adjacency matrix as Markov matrix, (ii) storing the weight (product of each edge weight ) of a random walk and using it as a factor if two walks meet and (iii) a combination of both. |
| Related Work | (2010) extend SimRank to edge weights , edge labels and multiple graphs. |