Báo cáo khoa học: "CD ER: Efficient MT Evaluation Using Block Movements" doc

... CDER: Efficient MT Evaluation Using Block Movements Gregor Leusch and Nicola Ueffing and Hermann Ney Lehrstuhl f ¨ ur ... well-known evaluation measures will be presented. Section 6 will conclude the paper and give an outlook on possible future work. 2 MT Evaluation 2.1 Block Reordering and State of the Art In MT – as ... tedious and cost-intensive, automatic evaluation me...

Ngày tải lên: 17/03/2014, 22:20

... set of metrics and meta-metrics for assessing MT quality (Gim ´ enez and M ` arquez, 2010a). Although automatic MT evaluation is still far from manual evaluation, it is indeed necessary to avoid ... to MT error analysis, and Section 6 concludes and reports some ongoing and future work. 2 The ASIYA Toolkit ASIYA is an open toolkit designed to assist devel- opers of both MT systems a...

Ngày tải lên: 16/03/2014, 20:20

... 237–240, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics splitSVM: Fast, Space -Efficient, non-Heuristic, Polynomial Kernel Computation for NLP Applications Yoav Goldberg and Michael ... Science POB 653 Be’er Sheva, 84105, Israel {yoavg,elhadad}@cs.bgu.ac.il Abstract We present a fast, space efficient and non- heuristic method for calculating the decision fun...

Ngày tải lên: 17/03/2014, 02:20

... information. 3 Experiments 3.1 PORT as an Evaluation Metric We studied PORT as an evaluation metric on WMT data; test sets include WMT 2008, WMT 2009, and WMT 2010 all-to-English, plus 2009, 2010 ... and 22.0% ties). 1 Introduction Automatic evaluation metrics for machine translation (MT) quality are a key part of building statistical MT (SMT) systems. They play two 1...

Ngày tải lên: 19/02/2014, 19:20

... automatically-produced with MT tools to determine cross-language lexi- calization sets of target words. The major goal of her work was to perform monolingual English WSD. Evaluation was performed ... described in Ta- ble 1. Some improvement might be achieved when using lemmatization. We wanted to see how well we can do by using sentences as they are extracted from the parallel c...

Ngày tải lên: 20/02/2014, 12:20

... these combined approaches: nom+pe, nom+hb, nom+hb+pe, and hb+pe. 6 Experimental Evaluation The aim of the experimental evaluation is to es- tablish if the nominalized pattern is useful to help 853 0 0.2 0.4 0.6 0.8 1 0 ... some point-wise verb selec- tional preferences carry relevant seman- tic information. Experiments using Word- Net as a gold standard show promising re- sults. Where a...

Ngày tải lên: 20/02/2014, 12:20

... Figure 1: Evaluation plane for NLP applications adequacy evaluation TIDES MT( 2002) precision recall precision recall faithfulness compactness l ow faithfulness compactness AS MT fluency evaluation TIDES MT( 2002) QA(2004) correctness ... ratio, evaluated using a low p/r ratio evaluation guideline package (an example of this is the adequacy evaluation for MT in TIDES 2002)...

Ngày tải lên: 20/02/2014, 16:20

... transfer-based MTs because the word order can be significantly changed through syntactic transfer. A transfer- based MT method using the phrase structure is studied here. 3.2 Base MT System We ... Translation for Transfer-based MT In order to verify effective measures of controlled translation for transfer-based MTs, we review the fundamentals of TDMT in this section. TDMT was trained...

Ngày tải lên: 08/03/2014, 21:20

... its origi- nal version, the document retrieval task was left to Google, in CLEF it is necessary to search in the CLEF document collection in order to return the documents supporting the answers. ... to 3) from the document pas- sages obtained previously. The system uses the Ngram Statistic Package (Banerjee and Pedersen, 2003) for that purpose. These n-grams are scored using the formul...

Ngày tải lên: 08/03/2014, 21:20

... automatic evaluation method using multiple evaluation results from a manual method. In the field of machine translation, Yasuda et al. (2003) proposed an automatic method that gives an evaluation ... evaluation results. If there is a set of summaries (pooled summaries) produced from a document (or multiple documents) and if these are evaluated manually, then we can estimate a...

Ngày tải lên: 17/03/2014, 04:20