automatic evaluation of chinese translation output

... essential for automatic evaluation of Chinese translation output. Our analysis suggests several key reasons behind this finding. 2 Chinese Translation Evaluation Automatic MT evaluation aims ... adopted as the smallest unit in most tasks of Chinese language processing. However, for automatic evaluation of the quali- ty of Chinese translation output when translat- ing from other languages, ... Linguistics Automatic Evaluation of Chinese Translation Output: Word-Level or Character-Level? Maoxi Li Chengqing Zong Hwee Tou Ng National Laboratory of Pattern Recognition Institute of Automation,...

Ngày tải lên: 17/03/2014, 00:20

... present the evaluations of ROUGE-L, ROUGE-S, and compare their per- formance with other automatic evaluation meas- ures. 5 Evaluations One of the goals of developing automatic evalua- tion ... averages of the adequacy and fluency scores of each system assigned by human evalua- tors. For the input of automatic evaluation meth- ods, we created three evaluation sets from the MT outputs: ... Quality Measure for Machine Translation System. In Proceedings of COLING-92, Nantes, France. Thompson, H. S. 1991. Automatic Evaluation of Translation Quality: Outline of Methodology and Report...

Ngày tải lên: 20/02/2014, 16:20

Ngày tải lên: 23/03/2014, 20:20

Ngày tải lên: 31/03/2014, 04:20

... Evaluation of Ma- chine Translation. Technical Report RC22176, IBM. Joseph Turian, Luke Shen, and I. Dan Melamed. 2003. Evalua- tion of Machine Translation and its evaluation. In Proceedings of MT ... grammar, rhythm and flow, appropriateness of tone, and several other specific characteristics of good text. In terms of automatic evaluation, we are not aware of any technique that measures only fluency ... source content with fluency of the resulting text. In this paper we develop an automatic evaluation metric to estimate fluency alone, by examin- ing the use of parser outputs as metrics, and show...

Ngày tải lên: 20/02/2014, 12:20

... highlights parts of the MT output that it suspects are non-grammatical. Even though the main purpose of BLAST is for error annotation of machine translation output, the freedom in the use of error typologies ... ref- erence translation. 1 Introduction Machine translation evaluation is a difficult task, since there is not only one correct translation of a sentence, but many equally good translation options. Often, ... developers. 2 MT Evaluation and Error Analysis Hovy et al. (2002) discussed the complexity of MT evaluation, and stressed the importance of adjusting evaluation to the purpose and context of the trans- lation....

Ngày tải lên: 07/03/2014, 22:20

... trans./word 4.21 Rewritten Translations  Original Translations Table 1: Comparison of TDMT Training Translations and Original Translations the rule writers rewrote translations to make tar- get ... words in the target language and the mean number of translation words, both values of the rewritten translations are lower than those of the original translations. This is because 1 When TDMT translates ... number of word links When it is calculated only from the sentences that contain four word links, the value of the rewritten transla- tions is higher than that of the original translations. 4 Translation...

Ngày tải lên: 08/03/2014, 21:20

... year of evaluation to the next. 5.2 Evaluation of rankings We examine the predictive power of our features for each of the five linguistic quality questions in two settings. In system-level evaluation, ... of systems, ignoring the linguistic quality of the system out- put. Part of the reason for this imbalance is the existence of ROUGE (Lin and Hovy, 2003; Lin, 2004), the system for automatic evaluation ... row of Table 1 that none of the system rankings based on these mea- sures of linguistic quality are significantly posi- tively correlated with system rankings of content. The development of automatic...

Ngày tải lên: 16/03/2014, 23:20

Ngày tải lên: 23/03/2014, 17:20

Ngày tải lên: 31/03/2014, 00:20

... 2003. Appli- cations of automatic evaluation methods to measuring a capability of speech translation system. In Proceed- ings of the 10th Conference of the European Chap- ter of the Association ... improve further. 7 Discussion 7.1 Other Automatic Evaluation Methods The idea of feedback cleaning is independent of BLEU. Some automatic evaluation methods of MT quality other than BLEU have been ... rules. 3 Automatic Evaluation of MT Quality We utilize BLEU (Papineni et al., 2002) for the au- tomatic evaluation of MT quality in this paper. BLEU measures the similarity between MT re- sults and translation...

Ngày tải lên: 08/03/2014, 04:22

Ngày tải lên: 31/03/2014, 20:20

... chal- lenge is the evaluation: manual evaluation is a difficult, time-consuming process and not ap- plicable within efficient development of sys- tems. Automatic evaluation requires a cor- pus of questions ... Y are known enemies. The problem of several possible answers and, in consequence, automatic evaluation has been tackled for years within another field of study: automatic summarisation (Hori et ... slow a rate of data acquisition. Therefore it is of- ten necessary to raise the reward and rely on efficient automatic validation of the data. We have looked into the answer agreement of the workers...

Ngày tải lên: 20/02/2014, 09:20

... collaboration of Professor Anthony Oettinger and of his other colleagues at the Harvard Computation Laboratory. semiautomatic synthesis of translation algorithms from empirical data, a means of formula ... Synthesis of Translation Algorithms by Vincent E. Giuliano*, Computation Laboratory of Harvard University A system of procedures and computer programs is proposed for the semi -automatic synthesis of ... predicates. Information enabling the automatic specifi- cation of each of these variables is present in the form of grammatical codes in the entries of the Harvard Automatic Dictionary. The indicated...

Ngày tải lên: 16/03/2014, 19:20

... of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 522–530, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Automatic Adaptation of Annotation Standards: Chinese ... efficacy of this method in the context of Chinese word segmentation and part -of- speech tagging, where no segmentation and POS tagging standards are widely accepted due to the lack of morphology in Chinese. ... latter problem often implies the former, as in our case study. To test the efficacy of our method we choose Chinese word segmentation and part -of- speech tagging, where the problem of incompatible...

Ngày tải lên: 17/03/2014, 01:20

... Assessments of Machine Translation Quality. In Proc. of MT Summit IX, 63–70. Hiroshi Echizen-ya and Kenji Araki. 2007. Auto- matic Evaluation of Machine Translation based on Recursive Acquisition of an ... Stephen Wan and Robert Dale. 2007. GLEU: Automatic Eval- uation of Sentence-Level Fluency. In Proc. of ACL’07, 344–351. NIST. 2002. Automatic Evaluation of Machine Translation Quality Us- ing N-gram ... with Applications to Machine Translation Evaluation. In Proc. of MT Summit IX, 240– 247. Chin-Yew Lin and Franz Josef Och. 2004. Auto- matic Evaluation of Machine Translation Qual- ity Using Longest...

Ngày tải lên: 23/03/2014, 16:20

Ngày tải lên: 23/03/2014, 18:20

Ngày tải lên: 24/03/2014, 03:20

Ngày tải lên: 31/03/2014, 06:20

Ngày tải lên: 01/04/2014, 00:20