Similar articles

Abstract: In machine translation (MT) practice, there is an urgent need for constructing a set of Chinese-to-English aspect transferring rules to define the transferring conditions. The integrated feature set was used to generalize and justify the Chinese-to-English transferring rule of the ‘ZHE’ aspect (ZHE Rule). A ZHE classification model was built in this study. The impacts of each set of temporal, lexical aspectual, and syntactic features, and their integrated impacts, on the accuracy of the ZHE Rule were tested. Over 600 misclassified corpus sentences were manually examined. A 10-fold cross-validation was used with a decision tree algorithm. The main results are: (1) The ZHE Rule was generalized and justified to have a higher accuracy under the two metrics: the precision rate and the areas under the receiver operating characteristic curve (AUC). (2) The temporal, lexical aspectual, and syntactic feature sets have an integrated contribution to the accuracy of the ZHE Rule. The syntactic and temporal features have an impact on ZHE aspect derivations, while the lexical aspectual features are not predictive of ZHE aspect derivation. (3) While associated with active verbs, the ZHE aspect can denote a perfective situation. This study suggests that the temporal and syntactic features are the predictive ZHE aspect classification features and that the ZHE Rule with an overall precision rate of 80.1% is accurate enough to be further explored in MT practice. The machine learning method, decision tree, can be applied to the automatic aspect transferring in MT research and aspectual interpretations in linguistic research.

[1]Chen, C.C., 2009. Ambiguity of LE in Chinese: the perfective as well as imperfective. J. Chin. Ling., 37(1):108-129.

[2]Chen, G., 1990. On the Usage of “ZHE” and Its Comparison with English Progressive. In: Yang, Z.J. (Ed.), Collected Papers on English-Chinese Contrastive Study. Shanghai Foreign Language Education Press, Shanghai, China, p.379-391 (in Chinese).

[3]Chen, Q.R., 2003. A Study on Chinese Aspectual System. PhD Thesis, Central China Normal University, Wuhan, China, p.142-152 (in Chinese).

[4]Cheng, J.H., Dai, X.Y., Chen, J.J., Wang, Q.X., 2004. Processing of tense and aspect in Chinese-English machine translation. Appl. Res. Comput., (3):79-80 (in Chinese).

[5]Dai, Y.J., 1997. A Study on the Aspectual System in Modern Mandarin Chinese. Zhejiang Education Publishing House, Hangzhou, China (in Chinese).

[6]Institute of Linguistics in Chinese Academy of Social Sciences, 2005. Xiandai Hanyu Cidian (5th Ed.). The Commercial Press Ltd., Beijing, China, p.1096 (in Chinese).

[7]Jin, L.X., 2003. The grammatical meaning of “S+le” structure and its syntactic requirements. Lang. Teach. Ling. Stud., 100(2):38-48 (in Chinese).

[8]Li, W.J., Wong, K.F., Cao, G.H., Yuan, C.F., 2004. Applying Machine Learning to Chinese Temporal Relation Resolution. 42nd Annual Meeting of the Association for Computational Linguistics, p.582-588.

[9]Lin, Z., 2004. The Grammaticalization of “Le1” from a Marker of Perfective to a Marker of Tense. In: Jing, C. (Ed.), Hanyu Shiti Xitong Guoji Yantaohui Lunwenji. Baijia Publishing House, Shanghai, China, p.86-102 (in Chinese).

[10]Ljungqvist, M., 2007. LE, GUO and ZHE in Mandarin Chinese: a relevance-theoretic account. J. East Asian Ling., 16(3):193-235.

[11]Lu, J.M., 1999. A supplementary comment on “ZHE”. Chin. Lang., 272(5):331-335 (in Chinese).

[12]Olsen, M., 1997. A Semantic and Pragmatic Model of Lexical and Grammatical Aspect. Garland Publishing, Inc., New York and London, p.163-191.

[13]Olsen, M., Traum, D., van Ess-Dykema, C., Weinberg, A., 2001. Implicit Cues for Explicit Generation: Using Telicity as a Cue for Tense Structure in a Chinese to English MT System. Proc. Machine Translation Summit VIII, p.34-41.

[14]Pan, W.G., 2004. A Study on the Aspects in Mandarin Chinese from a Perspective of the English Translation of “Le”. In: Jing, C. (Ed.), Hanyu Shiti Xitong Guoji Yantaohui Lunwenji. Baijia Publishing House, Shanghai, China, p.139-153 (in Chinese).

[15]Pen, L.Z., 2007. A Study on the Modern Mandarin Chinese Modes. China Social Science Press, Beijing, China, p.209-309 (in Chinese).

[16]Qian, N.Y., 2000. Aspect mark “zhe” not express “progressive” meaning. Chin. Lang. Learn., (4):25-30 (in Chinese).

[17]Qu, Y.H., 2008. A Chinese-English Comparative Study of Viewpoint Aspects: a Bilingual Corpus-Based Approach. Science Press, Beijing, China, p.74-84 (in Chinese).

[18]Qu, Y.H., Feng, Z.W., 2008. A study on the derivations of viewpoint aspects in Mandarin Chinese. J. Zhejiang Univ. (Human. Soc. Sci.), 38(4):173-181 (in Chinese).

[19]Qu, Y.H., Tao, T.J., Xu, C.Z., Feng, Z.W., 2008. The Formalization of ‘Temporal Adverbials+ZHE Imperfective’ Sentences. IEEE Int. Conf. on Natural Language Processing and Knowledge Engineering, p.375-382.

[20]Robson, S.Y., 2005. The temporal relations and aspects expressed by the particle LE in Mandarin Chinese. J. Chin. Ling., 33(2):333-365.

[21]Shang, X., 2007. The Comparative Studies between Chinese and English Aspect Systems. Shanghai People’s Publishing House, Shanghai, China (in Chinese).

[22]Shi, J.S., Hu, X.P., 1998. The “BA” structure with verbs followed by “ZHE”. Lang. Teach. Ling. Stud., (4):39-49 (in Chinese).

[23]Shi, Y.Z., 1992. Aspects in modern Chinese. Soc. Sci. China, (6):183-201 (in Chinese).

[24]Smith, C., 1991. The Parameter of Aspect. Kluwer Academic Publishers, Dordrecht, the Netherlands.

[25]Smith, C., 1997. The Parameter of Aspect (2nd Ed.). Kluwer Academic Publishers, Dordrecht, the Netherlands, p.273-277.

[26]Soh, H.L., 2009. Speaker presupposition and Mandarin Chinese sentence-final-Le: a unified analysis of the “change of state” and the “contrary to expectation” reading. Nat. Lang. Ling. Theory, 27(3):623-657.

[27]Sun, Y.J., 2007. Studies of the Mandarin Chinese Aspect System. Heilongjiang People’s Publishing House, Haerbin, China (in Chinese).

[28]Vendler, Z., 1957. Verbs and times. Philos. Rev., 66:143-160.

[29]Wang, K.F., 2004. The Construction and Application of the Bilingual and Parallel Corpus. Foreign Language Teaching and Research Press, Beijing, China, p.110 (in Chinese).

[30]Wong, S.M., Li, W.J., Wong, K.F., 2005. A Framework for Modeling and Representing Temporal Discourse Structure. Proc. IEEE Int. Conf. on Natural Language Processing and Knowledge Engineering, p.213-218.

[31]Wu, F.X., 2005. On the non-obligatory status of the Mandarin aspect markers “le” and “zhe”. Contemp. Ling., 7(3):237-250 (in Chinese).

[32]Xiao, X.Q., 2002. A comparative study on the functions of “ZHEN (ZAI)”, “ZAI” and “ZHE”. Ling. Study, (4):30-37 (in Chinese).

[33]Xiao, Z., Mcenery, T., 2004. Aspect in Mandarin Chinese: a Corpus-Based Study. In: Abraham, W., Noonan, M. (Eds.), Studies in Language Companion Series 73. John Benjamins, Amsterdam/Philadelphia, the Netherlands, p.181-205.

[34]Ye, Y., Zhang, Z., 2005. Tense Tagging for Verbs in Cross-Lingual Context: a Case Study. Proc. 2nd Int. Joint Conf. on Natural Language Processing, p.885-895.

[35]Ye, Y., Fossum, V.L., Abney, S., 2006. Latent Features in Temporal Reference Translation. Proc. 5th SIGHAN Workshop on Chinese Language Processing, p.48-55.

[36]Ye, Y., Schneider, K.M., Abney, S., 2007. Aspect Marker Generation in English-to-Chinese Machine Translation. Proc. Machine Translation Summit XI, p.521-527.

[37]Zhao, S.K., Shen, J.X., 1984. Mandarin “LE” and its target English expressions. Stud. Lang. Ling., 6(1):114-126 (in Chinese).