Learning Regular Languages from Positive Evidence
نویسندگان
چکیده
Children face an enormously difficult task in learning their native language. It is widely believed that they do not receive or make little use of negative evidence (Marcus, 1993), and yet it has been proven that many classes of languages less powerful than natural languages cannot be learned in the absence of negative evidence (Gold, 1964). In this paper we present an approach to learning good approximations to members of one such class of languages, the regular languages, based on positive evidence alone.
منابع مشابه
Learning of Partial Languages
In this paper we introduce a finite automaton called partial finite automaton to recognize partial languages. We have defined three classes of partial languages, viz., local partial languages, regular partial languages and partial line languages. We present an algorithm for learning local partial languages in the limit from positive data. The time taken for the algorithm to identify the regular...
متن کاملPartially Distribution-Free Learning of Regular Languages from Positive Samples
Regular languages are widely used in NLP today in spite of their shortcomings. Efficient algorithms that can reliably learn these languages, and which must in realistic applications only use positive samples, are necessary. These languages are not learnable under traditional distribution free criteria. We claim that an appropriate learning framework is PAC learning where the distributions are c...
متن کاملLearning (k, l)-Contextual Tree Languages for Information Extraction
Learning regular languages from positive examples only is known to be infeasible. A common solution is to define a learnable subclass of the regular languages. In the past, this has been done for regular string languages. Using ideas from those techniques, we define a learnable subclass of regular unranked tree languages, called the (k,l)-contextual tree languages. We describe the use of this s...
متن کاملMeta-algorithm GENMODEL: Generalizing over three learning settings using observation tables
We present a learning algorithm for regular languages that unifies three existing ones for the settings of minimally adequate teacher learning, learning from membership queries and positive data, and learning from positive and negative data, respectively. We choose these three algorithms as an example to back up the conjecture that the learning process of every algorithm for the class of regula...
متن کامل