2.2 Generic Collaborative Decoding Model For a given source sentence f, a member model in co-decoding finds the best translation 6* among the set of possible candidate translations if (f) based on a scoring function F:

where CIDm (f, e) is the score function of the mth baseline model, and each Wk(e,17-[k (f)) is a partial consensus score function with respect to dk and is defined over e and 17-[k (f):

Note that in Equation 2, though the baseline score function CIDm (f, 6) can be computed inside each decoder, the case of Wk (ail-[k (f)) is more complicated.

The PTs used in this work are constructed using different corpora and different score functions (Section 3.5).

Let (51,72) be a pair of paraphrase units, their paraphrase likelihood is computed using a score function ¢pm(§i,fi).

Suppose we have K PTs, (ski, {1%) is a pair of paraphrase units from the k-th PT with the score function gbk(§ki, £191.

unlabeled data), a model distribution p A(y|x), and a score function 8:

In this paper, we use a score function that is the squared difference of the model expectation of G and some target expectation G:

The partial derivative of the KL divergence score function includes the same covariance term as above but substitutes a different multiplicative term: G / G ,\.

We use this ranking to learn a linear scoring function on pairs of documents given a bilingual query.

these heuristics and our learned pairwise scoring function , we can derive a ranking for new, unseen bilingual queries.

Then we learn a linear scoring function for pairs of documents that exploits monolingual information (in both languages) and bilingual information.

the retrieved questions is formalized using a scoring function .

Based on the weight function, we define a scoring function for assigning a score to each question in the corpus Q.

For each token 3,, the scoring function chooses the term from Q haVing the maximum weight; then the weight of the n chosen terms are summed up to get the score.