We consider two scenarios, 1) Monolingual samples in the source and target languages are available and 2) An additional small amount of parallel corpus is also available.

In this section we address scenario 81: we have access to a source-language monolingual collection (from which portions to be manually translated could be sampled) and a target-language in—domain monolingual corpus, to supplement the target side of a parallel corpus while training a language model.

5 Extrapolating a learning curve fitted on a small parallel corpus

Given a small “seed” parallel corpus , the translation system can be used to train small in-domain models and the evaluation score can be measured at a few initial sample sizes {($1,y1), ($2, yg)...(acp, yp)}.

In the first scenario ($1), the SMT developer is given only monolingual source and target samples from the relevant domain, and a small test parallel corpus .

In the second scenario (S2), an additional small seed parallel corpus is given that can be used to train small in-domain models and measure (with some variance) the evaluation score at a few points on the initial portion of the learning curve.

For a certain bilingual test dataset d, we consider a set of observations 0d 2 {(301, yl), ($2, yg)...(;vn, 3471)}, where y, is the performance on d (measured using BLEU (Papineni et al., 2002)) of a translation model trained on a parallel corpus of size 307;.

The corpus size 307; is measured in terms of the number of segments (sentences) present in the parallel corpus .

English), unlabeled parallel corpus U of the source language and the target language, and optional labeled data DT in target language T. Aligning with previous work (Wan, 2008; Wan, 2009), we only consider binary sentiment classification scheme (positive or negative) in this paper, but the proposed method can be used in other classification schemes with minor modifications.

The basic idea underlying CLMM is to enlarge the vocabulary by learning sentiment words from the parallel corpus .

More formally, CLMM defines a generative mixture model for generating a parallel corpus .

By “synchronizing” the generation of words in the source language and the target language in a parallel corpus, the proposed model can (1) improve vocabulary coverage by learning sentiment words from the unlabeled parallel corpus; (2) transfer polarity label information between the source language and target language using a parallel corpus .

the authors use an unlabeled parallel corpus instead of machine translation engines.

They propose a method of training two classifiers based on maximum entropy formulation to maximize their prediction agreement on the parallel corpus .

5.1.2 Parallel Corpus

Our parallel corpus is crawled from the web, containing news articles, technical documents, blog entries etc.

We use Giza++ (Och and Ney, 2003) to generate the word alignment for the parallel corpus .

In this section, we first describe how to extract reordering examples from parallel corpus ; then we show our features for ranking function; finally, we discuss how to train the model from the extracted examples.

This paper proposes a novel graph-based projection approach and demonstrates the merits of it by using a Korean relation extraction system based on projected dataset from an English—Korean parallel corpus .

To accomplish that goal, the method automatically creates a set of annotated text for ft, utilizing a well-made extractor f3 for a resource-rich source language L3 and a parallel corpus of LS and Lt.

where count (us, ut) is the number of alignments between us and ut across the whole parallel corpus .

We used an English-Korean parallel corpus 1 that contains 266,892 bi-sentence pairs in English and Korean.

1The parallel corpus collected is available in our website: http://isoft.postech.ac.kr/"megaup/acl/datasets thtpzllreverbcs.washington.edu/

The English sentence annotations in the parallel corpus were then propagated into the corresponding Korean sentences.

Without using extra paraphrase resources, we acquire the rules by comparing the source side of the parallel corpus with the target-to-source translations of the target side.

We train a source-to-target PBMT system (SYS_ST) and a target-to-source PBMT system (SYS_TS) on the parallel corpus .

Note that all the texts of S0, S1, S2, T 0 and T1 are sentence aligned because the initial parallel corpus (S0, T 0) is aligned in the sentence level.