Based on these measures, we improve the alignment quality by selecting high confidence sentence alignments and alignment links from multiple word alignments of the same sentence pair .

Similar to the sentence alignment confidence measure, the confidence of an alignment link aij in the sentence pair (S, T) is defined as

From multiple alignments of the same sentence pair , we select high confidence links from different alignments based on their link confidence scores and alignment agreement ratio.

Suppose the sentence pair (8, T) have alignments A1,.

512 sentence pairs, and the A-E alignment test set is the 200 Arabic-English sentence pairs from NIST MT03 test set.

The example in Figure 1 shows the word alignment of the given Chinese and English sentence pair , where the English words following each Chinese word is its literal translation.

In this paper we introduce a confidence measure for word alignment, which is robust to extra or missing words in the bilingual sentence pairs , as well as word alignment errors.

Given a bilingual sentence pair (S,T) where S={31,. .

We randomly selected 512 Chinese-English (CE) sentence pairs and generated word alignment using the MaxEnt aligner (Ittycheriah and Roukos, 2005).

For each sentence pair , we also calculate the sentence alignment confidence score — log 0 (A|S, T).

In this paper, we applied a graph-based SSL algorithm to improve the performance of QA task by exploiting unlabeled entailment relations between affirmed question and candidate sentence pairs .

We also used a set of 340 QA-type sentence pairs from RTE02-03 and 195 pairs from RTE04 by converting the hypothesis sentences into question form to create additional set of q/a pairs.

Each of these headline-candidate sentence pairs is used as additional unlabeled q/a pair.

This is due to the fact that we establish two seperate entailment models for copula and non-copula q/a sentence pairs that enables extracting useful information and better representation of the specific data.

(2) (QComp) Question component match features: The sentence component analysis is applied on both the affirmed question and the candidate sentence pairs to characterize their semantic components including subject(S), object(O), head (H) and modifiers(M).

Let each data point in X = {531, ..., an}, xi E SW represents information about a question and candidate sentence pair and Y = {3/1, be their output labels.

2.1 Minimum Bayes Risk over Sentence Pairs

Algorithm 1 MBR over Sentence Pairs 12 A <— —00 2: for e E E do 3: A6 <— 0 4 for e’ E E do 5: Ae<—A6+P(e’|f)-S(e;e’) 6 7

MBR over Sentence Pairs MBR over Features

A phrase discovery procedure over word-aligned sentence pairs provides rule frequency counts, which are normalized to estimate features on rules.

The synchronous grammar rules are extracted from word aligned sentence pairs where the target sentence is annotated with a syntactic parse (Galley et al., 2004).

Figure 1(b) shows an aligned sentence pair example where dependencies are perfectly conserved across the alignment.

For example, in some sentence pair we might find 10 edges that have both end points aligned and can be transferred.

Our basic model uses constraints of the form: the expected proportion of conserved edges in a sentence pair is at least 77 = 90%.1

In grammar transfer, our basic constraint is of the form: the expected proportion of conserved edges in a sentence pair is at least 77 (the exact proportion we used was 0.9, which was determined using unlabeled data as described in Section 5).

9We used about 70k sentence pairs for CE model training, while Wang et a1.

(2008) used about 100k sentence pairs , a CE translation dictionary and more monolingual corpora for model training.

For English-Spanish translation, we selected 400k sentence pairs from the Europarl corpus that are close to the English parts of both the BTEC CE corpus and the BTEC ES corpus.

Another way to use the synthetic multilingual corpus is to add the source-pivot or pivot-target sentence pairs in this corpus to the training data to rebuild the source-pivot or pivot-target SMT model.

Table 4: Comparison of rule extraction time (seconds/ 1000 sentence pairs ) and decoding time (sec-ond/sentence)

Table 4 gives the rule extraction time (seconds/ 1000 sentence pairs ) and decoding time (sec-ond/sentence) with varying pruning thresholds.

the new training corpus contained about 260K sentence pairs with 7.39M Chinese words and 9.41M English words.

Each language consists of 1500—2800 sentence pairs produced by 7—15 MT systems.

RTER has a rather flat learning curve that climbs to within 2 points of the final correlation value for 20% of the training set (about 400 sentence pairs ).

The average total runtime per sentence pair is 5 seconds on an AMD 2.6GHz Opteron core — efficient enough to perform regular evaluations on development and test sets.

We trained the system on the NIST MT06 Eval corpus excluding the UN data (approximately 900K sentence pairs ).

We trained the system on a subset of 950K sentence pairs from the NIST MT08 training data, selected by

The subsampling algorithm selects sentence pairs from the training data in a way that seeks reasonable representation for all n-grams appearing in the test set.