Adaptation for statistical language model

摘要

Architecture that suppresses the unexpected appearance of words by applying appropriate restrictions to long-term and short-term memory. The quickness of adaptation is also realized by leveraging the restriction. The architecture includes a history component for processing user input history for conversion of a phonetic string by a conversion process that output conversion results, and an adaptation component for adapting the conversion process to the user input history based on restriction(s) applied to short-term memory that impacts word appearances during the conversion process. The architecture performs probability boosting based on context-dependent probability differences (short-term memory), and dynamic linear-interpolation between long-term memory and baseline language model based on frequency of preceding context of word (long-term memory).

主权项

1. A computer-implemented phonetic system, comprising:
a history component configured to process user input history for conversion of a phonetic string by a conversion process; a restriction component configured to apply the restriction by boosting a probability based on the context-dependent probability differences; an adaptation component configured to adapt the conversion process based on one or more restrictions applied to the user input history, which user input history comprises short-term memory as context-dependent probability differences and long-term memory as frequency of preceding context of a word, the adaptation component adapts the conversion process to the user input history to suppress unexpected word appearances during the conversion process; and a microprocessor configured to execute computer-executable instructions associated with the history component, the restriction component, and the adaptation component.