Methods and apparatus for generating dialog state conditioned language models
View Patent ↗Techniques are provided for generating improved language modeling. Such improved modeling is achieved by conditioning a language model on a state of a dialog for which the language model is employed. For example, the techniques of the invention may improve modeling of language for use in a speech recognizer of an automatic natural language based dialog system. Improved usability of the dialog system arises from better recognition of a user's utterances by a speech recognizer, associated with the dialog system, using the dialog state-conditioned language models. By way of example, the state of the dialog may be quantified as: (i) the internal state of the natural language understanding part of the dialog system; or (ii) words in the prompt that the dialog system played to the user.
1. A method for use in accordance with a dialog system, the dialog system comprising a processor, the method comprising the steps of:
generating by the processor of the dialog system at least one language model, the at least one language model being conditioned on a state of dialog associated with the dialog system; and
storing the at least one language model for subsequent use in accordance with a speech recognizer associated with the dialog system;
wherein the step of generating the at least one language model conditioned on a state of dialog associated with the dialog system further comprises the processor of the dialog system performing the steps of:
dividing training data which is labeled by state into different state sets depending on the state to which the training data belongs; and
building a separate language model for each of the state sets;
wherein at least a given state corresponds to an internal state of a natural language understanding portion of the dialog system;
wherein at least a given state corresponds to a prompt that the dialog system presents to a user;
wherein at least a given separate language model is interpolated with a base model obtained from available training data for a domain of the dialog system;
wherein the method further comprises the step of clustering together two or more state sets to reduce the number of states for which a separate language model is built; and
wherein a decision to cluster two states is based on a distance measure computed between respective word distributions associated with the two states
wherein each separate language model is built using a modified Kneser-Ney smoothing technique.