Maximum Entropy Models for Realization Ranking
نویسندگان
چکیده
In this paper we describe and evaluate different statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations generated for a given input semantics. Three models are trained and tested; an n-gram language model, a discriminative maximum entropy model using structural features, and a combination of these two. Our realization component forms part of a larger, hybrid MT system.
منابع مشابه
Statistical Ranking in Tactical Generation
In this paper we describe and evaluate several statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations generated for a given input semantics. Three models (and several variants) are trained and tested: an n-gram language model, a discriminative maximum entropy model using structural information (and incorporating the lang...
متن کاملFeature Selection for Fluency Ranking
Fluency rankers are used in modern sentence generation systems to pick sentences that are not just grammatical, but also fluent. It has been shown that feature-based models, such as maximum entropy models, work well for this task. Since maximum entropy models allow for incorporation of arbitrary real-valued features, it is often attractive to create very general feature templates, that create a...
متن کاملA Note on the Bivariate Maximum Entropy Modeling
Let X=(X1 ,X2 ) be a continuous random vector. Under the assumption that the marginal distributions of X1 and X2 are given, we develop models for vector X when there is partial information about the dependence structure between X1 and X2. The models which are obtained based on well-known Principle of Maximum Entropy are called the maximum entropy (ME) mo...
متن کاملMaximum Entropy and Variable Strength
A new algorithm for computing the maximum entropy ranking over models is presented. The algorithm handles arbitrary sets of proposi-tional defaults with associated strength assignments and succeeds whenever the set satisses a robustness condition. Failure of this condition implies the problem may not be suuciently speciied for a unique solution to exist. This work extends the applicability of t...
متن کاملMaximum Entropy and Variable Strength Defaults
A new algorithm for computing the maximum entropy ranking over models is presented. The algorithm handles arbitrary sets of propositional defaults with associated strength assignments and succeeds whenever the set satisfies a robustness condition. Failure of this condition implies the problem may not be sufficiently specified for a unique solution to exist. This work extends the applicability o...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005