Automatic Inference of the Temporal Location of Situations in Chinese Text
44850Authors
nan
Abstract
Chinese is a language that does not have mor- phological tense markers that provide explicit grammaticalization of the temporal location of situations (events or states). However, in many NLP applications such as Machine Transla- tion, Information Extraction and Question An- swering, it is desirable to make the temporal location of the situations explicit. We describe a machine learning framework where differ- ent sources of information can be combined to predict the temporal location of situations in Chinese text. Our experiments show that this approach significantly outperforms the most frequent tense baseline. More importantly, the high training accuracy shows promise that this challenging problem is solvable to a level where it can be used in practical NLP applica- tions with more training data, better modeling techniques and more informative and general- izable features. 1
Keywords
Full Content
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 707–714, Honolulu, October 2008. c⃝2008 Association for Computational Linguistics Automatic inference of the temporal location of situations in Chinese text Nianwen Xue Center for Computational Language and Education Research University of Colorado at Boulder Colorado, U.S.A. Nianwen.Xue@colorado.edu Abstract Chinese is a language that does not have mor- phological tense markers that provide explicit grammaticalization of the temporal location of situations (events or states). However, in many NLP applications such as Machine Transla- tion, Information Extraction and Question An- swering, it is desirable to make the temporal location of the situations explicit. We describe a machine learning framework where differ- ent sources of information can be combined to predict the temporal location of situations in Chinese text. Our experiments show that this approach significantly outperforms the most frequent tense baseline. More importantly, the high training accuracy shows promise that this challenging problem is solvable to a level where it can be used in practical NLP applica- tions with more training data, better modeling techniques and more informative and general- izable features. 1 Introduction In a language like English, tense is an explicit (and maybe imperfect) grammaticalization of the tempo- ral location of situations, and such temporal location is either directly or indirectly defined in relation to the moment of speech. Chinese does not have gram- maticalized tense in the sense that Chinese verbs are not morphologically marked for tense. This is not to say, however, that Chinese speakers do not at- tempt to convey the temporal location of situations when they speak or write, or that they cannot inter- pret the temporal location when they read Chinese text, or even that they have a different way of repre- senting the temporal location of situations. In fact, there is evidence that the temporal location is rep- resented in Chinese in exactly the same way as it is represented in English and most world languages: in relation to the moment of speech. One piece of evi- dence to support this claim is that Chinese temporal expressions like �� (“today”), �� (“tomorrow”) and �� (“yesterday”) all assume a temporal deixis that is the moment of speech in relation to which all temporal locations are defined. Such temporal expressions, where they are present, give us a clear indication of the temporal location of the situations they are associated with. However, not all Chinese sentences have such temporal expressions associated with them. In fact, they occur only infrequently in Chinese text. It is thus theoretically interesting to ask, in the absence of grammatical tense and explicit temporal expressions, how do readers of a particular piece of text interpret the temporal location of situa- tions? There are a few linguistic devices in Chinese that provide obvious clues to the temporal location of situations, and one such linguistic device is aspect markers. Although Chinese does not have grammat- ical tense, it does have grammaticalized aspect in the form of aspect markers. These aspect markers often …
Content truncated to 500 words
Labeled Text
Chinese is a language that does not have morphological tense markers that provide explicit grammaticalization of the temporal location of situations (events or states). However, in many NLP applications such as Machine Translation, Information Extraction and Question Answering, it is desirable to make the temporal location of the situations explicit. We describe a machine learning framework where different sources of information can be combined to predict the temporal location of situations in Chinese text. Our experiments show that this approach significantly outperforms the most frequent tense baseline. More importantly, the high training accuracy shows promise that this challenging problem is solvable to a level where it can be used in practical NLP applications with more training data, better modeling techniques and more informative and generalizable features. 1
Publication Details
- Paper ID:
- 44850
- Year:
- 2008
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan