A proposal to develop domain and subtask-adaptive dialog management models
نویسندگان
چکیده
Statistical dialog management techniques have the main advantage of allowing an easy adaptation of the dialog model to different application domains. In this paper we propose to also adapt the operation of the dialog manager to the different subtasks that conform the structure of the dialog in each domain. To do so, we present a variation of a statistical dialog management technique to address this challenge. The evaluation results with a practical dialog system show that the use of such specific sub-task models increase the quality and number of successful interactions with the system.
منابع مشابه
Learning the Structure of Task-Driven Human-Human Dialogs
Data-driven techniques have been used for many computational linguistics tasks. Models derived from data are generally more robust than hand-crafted systems since they better reflect the distribution of the phenomena being modeled. With the availability of large corpora of spoken dialog, dialog management is now reaping the benefits of data-driven techniques. In this paper, we compare two appro...
متن کاملIncremental Parsing Models for Dialog Task Structure
In this paper, we present an integrated model of the two central tasks of dialog management: interpreting user actions and generating system actions. We model the interpretation task as a classication problem and the generation task as a prediction problem. These two tasks are interleaved in an incremental parsing-based dialog model. We compare three alternative parsing methods for this dialog...
متن کاملYJTI at the NTCIR-13 STC Japanese Subtask
In this paper, we describe our participation in the NTCIR-13 STC Japanese Subtask, in which we develop systems with the retrieval-based method. To retrieve reply texts for a given comment text, our system generates vector representations of both the comment and candidate replies by a 3-layer LSTM-RNN and evaluate distances between the comment vector and the candidate reply vectors, selecting th...
متن کاملModelling Multi-issue Bargaining Dialogues: Data Collection, Annotation Design and Corpus
The paper describes experimental dialogue data collection activities, as well semantically annotated corpus creation undertaken within EU-funded METALOGUE project. The project aims to develop a dialogue system with flexible dialogue management to enable systems adaptive, reactive, interactive and proactive dialogue behaviour in setting goals, choosing appropriate strategies and monitoring numer...
متن کاملA Multiple Adaptive Neuro-Fuzzy Inference System for Predicting ERP Implementation Success
The implementation of modern ERP solutions has introduced tremendous opportunities as well as challenges into the realm of intensely competent businesses. The ERP implementation phase is a very costly and time-consuming process. The failure of the implementation may result in the entire business to fail or to become incompetent. This fact along with the complexity of data streams has led ...
متن کامل