Using Probabilistic Feature Matching to Understand Spoken Descriptions
نویسندگان
چکیده
We describe a probabilistic reference disambiguation mechanism developed for a spoken dialogue system mounted on an autonomous robotic agent. Our mechanism performs probabilistic comparisons between features specified in referring expressions (e.g., size and colour) and features of objects in the domain. The results of these comparisons are combined using a function weighted on the basis of the specified features. Our evaluation shows high reference resolution accuracy across a range of spoken referring expressions.
منابع مشابه
ارائه یک مدل احتمالاتی جهت تعیین انسجام متن در سیستم های پرسش و پاسخ تعاملی
Evaluation plays an important role in interactive question answering systems like many computational linguistics fields. The coherence between the questions and the answers exchanged between the user and the system is one of the important criteria in evaluating these systems. In this paper, a new approach to determine the degree of coherence of generated text by the IQA systems is presented. Th...
متن کاملSemantic processing survey of spoken and written words in adolescents with cerebral palsy: Evidence from PALPA word-picture matching test
Objective: The present study aimed to assess and compare semantic processing of spoken and written words in adolescents with cerebral palsy and healthy adolescents. Method: The present study is quantitative in terms of type and experimental in terms of method. Examination Group consisted 30 adolescents with cerebral palsy aged 10 to 15 years were selected by convenience sampling method. All of ...
متن کاملA Trainable Visually-grounded Spoken Language Generation System
A spoken language generation system has been developed that learns to describe objects in computer-generated visual scenes. The system is trained by a ‘show-and-tell’ procedure in which visual scenes are paired with natural language descriptions. Learning algorithms acquire probabilistic structures which encode the visual semantics of phrase structure, word classes, and individual words. Using ...
متن کاملA unified probabilistic generative framework for extractive spoken document summarization
In this paper, we consider extractive summarization of Chinese broadcast news speech. A unified probabilistic generative framework that combined the sentence generative probability and the sentence prior probability for sentence ranking was proposed. Each sentence of a spoken document to be summarized was treated as a probabilistic generative model for predicting the document. Two different mat...
متن کاملA Probabilistic Model for Understanding Composite Spoken Descriptions
We describe a probabilistic reference disambiguation mechanism developed for a spoken dialogue system mounted on an autonomous robotic agent. Our mechanism receives as input referring expressions containing intrinsic features of individual concepts (lexical item, size and colour) and features involving more than one concept (ownership and location). It then performs probabilistic comparisons be...
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 2008