Strategies for optimizing a stochastic spoken natural language parser

نویسندگان

  • Wolfgang Minker
  • Dirk Bühler
  • Christiane Beuschel
چکیده

Strategies to enhance the semantic decoding accuracy of a stochastic parser are discussed and comparatively evaluated on the English Spontaneous Speech Task for multilingual appointment scheduling. The performance of the parser could be improved by subsequently adding valuable and removing redundant semantic information as well as by iteratively combining several decoding methods.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Chart Parsing of Stochastic Spoken Language Models

Performance in speech recognition systems has progressed to the point where it is now realistic to begin integrating speech with natural language systems to produce spoken language systems. Two factors have contributed to the advances in speech: statistical modeling of the input signal and language constraints. To produce spoken language systems, then, the grammar formalisms used in natural lan...

متن کامل

Stochastic Spoken Natural Language Parsing in the Framework of the French MEDIA Evaluation Campaign

A stochastic parsing component has been applied on a French spoken language dialogue corpus, recorded in the framework of theMEDIA evaluation campaign. Realized as an ergodic HMM using Viterbi decoding, the parser outputs the most likely semantic representation given a transcribed utterance as input. The semantic sequences used for training and testing have been derived from the semantic repres...

متن کامل

Response Generation in Dialogue Using a Tailored PCFG Parser

This paper presents a parsing paradigm for natural language generation task, which learns a tailored probabilistic context-free grammar for encoding meaning representation (MR) and its corresponding natural language (NL) expression, then decodes and yields natural language sentences at the leaves of the optimal parsing tree for a target meaning representation. The major advantage of our method ...

متن کامل

Stochastic language models for speech recognition and understanding

Stochastic language models for speech recognition have traditionally been designed and evaluated in order to optimize word accuracy. In this work, we present a novel framework for training stochastic language models by optimizing two different criteria appropriate for speech recognition and language understanding. First, the language entropy and salience measure are used for learning the releva...

متن کامل

Adult’s Learning Strategies for Receptive Skill Self-managing or Teacher-managing

Receptive language skill refers to answering appropriately to another person's spoken language. A lot of teachers try to develop receptive language skills in their language learners. When receptive language skills are not appropriately acquired, learners may miss significant learning opportunities resulting in delays in the development and acquisition of spoken language. The goals of this paper...

متن کامل

ذخیره 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 2004