Learning Local Transductions Is Hard
نویسنده
چکیده
Local deterministic string-to-string transductions are generalizations of morphisms on free monoids. Learning local transductions reduces to inference of monoid morphisms. However, learning a restricted class of morphisms, the so-called fine morphisms, is an intractable problem, because the decision version of the empirical risk minimization problem contains an NP-complete subproblem.
منابع مشابه
On the Expressivity of Linear Transductions
We investigate the formal expressivity properties of linear transductions, the class of transductions generated by linear transduction grammars, linear inversion transduction grammars and preterminalized linear inversion transduction grammars. While empirical results such as those in previous work are of course an ultimate test of modeling adequacy for machine translation applications, it is eq...
متن کاملAn integrated approach for scheduling flexible job-shop using teaching–learning-based optimization method
In this paper, teaching–learning-based optimization (TLBO) is proposed to solve flexible job shop scheduling problem (FJSP) based on the integrated approach with an objective to minimize makespan. An FJSP is an extension of basic job-shop scheduling problem. There are two sub problems in FJSP. They are routing problem and sequencing problem. If both the sub problems are solved simultaneously, t...
متن کاملInference of Inversion Transduction Grammars
We present the first polynomial algorithm for learning a class of inversion transduction grammars (itgs) that implement context free transducers – functions from strings to strings. The class of transductions that we can learn properly includes all subsequential transductions. These algorithms are based on a generalisation of distributional learning; we prove correctness of our algorithm under ...
متن کاملLinear Transduction Grammars and Zipper Finite-State Transducers
We examine how the recently explored class of linear transductions relates to finite-state models. Linear transductions have been neglected historically, but gainined recent interest in statistical machine translation modeling, due to empirical studies demonstrating that their attractive balance of generative capacity and complexity characteristics lead to improved accuracy and speed in learnin...
متن کاملTranslation as Linear Transduction Models and Algorithms for Efficient Learning in Statistical Machine Translation
Saers, M. 2011. Translation as Linear Transduction. Models and Algorithms for Efficient Learning in Statistical Machine Translation. Acta Universitatis Upsaliensis. Studia Linguistica Upsaliensia 9. 133 pp. Uppsala. ISBN 978-91-554-7976-3. Automatic translation has seen tremendous progress in recent years, mainly thanks to statistical methods applied to large parallel corpora. Transductions rep...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Journal of Logic, Language and Information
دوره 13 شماره
صفحات -
تاریخ انتشار 2004