Towards Combining Finite State, Ontologies, and Data Driven Approaches to Dialogue Management for Multimodal Question Answering
نویسنده
چکیده
Information-providing dialogue systems typically use one of the following dialogue strategies: finite-state based, frame-based, or agentbased. Recent extensions are concerned with hybrid models, where mixed automaton and information state approaches are combined. We report on our multimodal mobile Semantic Web access system SMARTWEB which uses a more rigid dialogue management strategy to ensure operability and robustness of the system while allowing for flexible dialogical interaction in a question answering scenario. In addition, a strategy to incorporate information state approaches into the running system to be extended towards a machine learning scenario for very particular, e.g. domain or language specific, dialogue management decisions is proposed. Korak h kombiniranju končnih avtomatov, ontologij in pristopov na podlagi podatkov za vodenje dialoga pri multimodalnem odgovarjanju na vprašanja Sistemi dialoga za dajanje informacij običajno uporabljajo eno od strategij, značilnih za dialog: takšno, ki temelji bodisi na končnih avtomatih, na okvirih ali agentih. Najnovejše širitve se ukvarjajo s hibridnimi modeli, pri katerih se kombinirata pristopa avtomatov in informacijskega stanja. V prispevku predstavljamo svoj multimodalni mobilni sistem SMARTWEB za dostopanja do mreže Semantic Web, ki uporablja bolj togo strategijo vodenja dialoga in s tem zagotavlja operabilnost in robustnost sistema, hkrati pa dovoljujemo prilagodljivo dialoško interakcijo v scenariju odgovarjanja na vprašanja. Poleg tega predlagamo strategijo za vključevanje pristopov informacijskega stanja v delujoč sistem, ki bi se razširil v scenarij strojnega učenja za zelo specifične odločitve vodenja dialoga, npr. za določeno področje ali jezik.
منابع مشابه
Towards Interaction Ontologies for Mobile Devices Accessing the Semantic Web Pattern Languages for Open Domain Information Providing Multimodal Dialogue Systems
We try to develop a communication basis between interface designers, natural language processing experts and scenario experts for multimodal dialogue systems. The question we address is, how to represent different kinds of results (information design) and interaction metaphors (interaction and presentation design) which are created and presented to the user during the dialogue. We present a pat...
متن کاملVidiam: Corpus-based Development of a Dialogue Manager for Multimodal Question Answering
In this chapter we describe the Vidiam project, which concerns the development of a dialogue management system for multi-modal question answering dialogues as it was carried out in the IMIX project. The approach that was followed is data-driven, that is, corpus-based. Since research in Question Answering Dialog for multi-modal information retrieval is still new, no suitable corpora were availab...
متن کاملA Multimodal Result Ontology for Integrated Semantic Web Dialogue Applications
General purpose ontologies and domain ontologies make up the infrastructure of the Semantic Web, which allow for accurate data representations with relations, and data inferences. In our approach to multimodal dialogue systems providing question answering functionality (SMARTWEB), the ontological infrastructure is essential. We aim at an integrated approach in which all knowledge-aware system m...
متن کاملMultimodal Dialogue Management - State of the art
This report is about the state of the art in dialogue management. We first introduce an overview of a multimodal dialogue system and its components. Second, four main approaches to dialogue management are described (finite-state and frame-based, information-state based and probabilistic, plan-based, and collaborative agent-based approaches). Finally, the dialogue management in the recent dialog...
متن کاملSome Issues in Dialogue-Based Question-Answering
We present on-going work on how to combine a multimodal dialogue system with techniques from information extraction and question-answering systems. A first combined system including both dialogue features and information extraction (BirdQuest) is presented. We conclude by listing a number of issues for further research. Combining dialogue and document processing In the field of Question Answeri...
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 2006