Hidden Understanding Models of Natural Language
نویسندگان
چکیده
We describe and evaluate hidden understanding models, a statistical learning approach to natural language understanding. Given a string of words, hidden understanding models determine the most likely meaning for the string. We discuss 1) the problem of representing meaning in this framework, 2) the structure of the statistical model, 3) the process of training the model, and 4) the process of understanding using the model. Finally, we give experimental results, including results on an ARPA evaluation.
منابع مشابه
Statistical Language Processing Using Hidden Understanding Models
This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models derives from statistical models used in speech recognition, especially the use of hidden Markov models. These techniques are applied to the central problem of determining meaning directly from a sequence of spoken or ...
متن کاملAn Empirical Exploration of Hidden Markov Models: From Spelling Recognition to Speech Recognition
Hidden Markov models play a critical role in the modelling and problem solving of important AI tasks such as speech recognition and natural language processing. However, the students often have difficulty in understanding the essence and applications of Hidden Markov models in the context of a cursory introductory coverage of the subject. In this paper, we describe an empirical approach to expl...
متن کاملLearning Conditional Random Fields from Unaligned Data for Natural Language Understanding
In this paper, we propose a learning approach to train conditional random fields from unaligned data for natural language understanding where input to model learning are sentences paired with predicate formulae (or abstract semantic annotations) without word-level annotations. The learning approach resembles the expectation maximization algorithm. It has two advantages, one is that only abstrac...
متن کاملUnderstanding Hidden Memories of Recurrent Neural Networks
Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, the lack of understanding of the mechanisms behind their effectiveness limits further improvements on their architectures. In this paper, we present a visual analytics method for understanding and comparing RNN models ...
متن کاملHidden Markov Models Suitable for Text Generation
The paper presents the application of Hidden Markov Models to text generation in Polish language. A program generating text, taking advantage of Hidden Markov Models was developed. The program uses a reference text to learn the possible sequences of letters. The results of text processing have been also discussed. The presented approach can be also helpful in speech recognition process. Key-Wor...
متن کامل