PCQL: A Formalism for Human-Like Preference Dialogues∗
نویسندگان
چکیده
Preference dialogues display several interesting characteristics that have implications on how to design human-like dialogue strategies in conversational recommender systems. Using human-human preference dialogues as an empirical base, this paper introduces a novel data manipulation language called PCQL that comprises explicit descriptive, comparative and superlative preference management as well as implicit preference statements such as factual information queries. The usage of the PCQL language is demonstrated by an implementation of a music conversational recommender system.
منابع مشابه
Agent Ludens: Games for Agent Dialogues
By treating dialogues as abstract games, we are able to develop a logic-based formalism for modeling of dialogues between intelligent and autonomous software agents. Complex dialogues, including dialogues embedded in one another, can be represented in the formalism as sequences of moves in a combination of dialogue games. We show that our formalism can represent the different types of dialogue ...
متن کاملDialogue Behavior Management in Conversational Recommender Systems
This thesis examines recommendation dialogue, in the context of dialogue strategy design for conversational recommender systems. The purpose of a recommender system is to produce personalized recommendations of potentially useful items from a large space of possible options. In a conversational recommender system, this task is approached by utilizing natural language recommendation dialogue for...
متن کاملExtraction de préférences à partir de dialogues de négociation (Towards Preference Extraction From Negotiation Dialogues) [in French]
Towards Preference Extraction From Negotiation Dialogues This paper presents an NLP based approach for preference expression extraction from negotiation dialogues. We propose a new annotation schema for preferences and dependencies among them and illustrate on two different corpus genres. We then suggest a learning approach that efficiently extracts preference expressions using a combination of...
متن کاملEvaluating humanoid synthetic agents in e-retail applications
This paper presents three experiments designed to empirically evaluate humanoid synthetic agents in electronic retail applications. Firstly, human-like agents were evaluated in a single e-retail application, a home furnishings service. The second experiment explored application dependency effects by evaluating the same human-like agents in a different e-retail application, a personalized CD ser...
متن کاملUsing MMIL for the High Level Semantic Annotation of the French MEDIA Dialogue Corpus
The MultiModal Interface Language formalism (MMIL) has been selected as the High Level Semantic (HLS) formalism for annotating the French MEDIA dialogue corpus. This corpus is composed of human-machine dialogues in the domain of hotel reservation and tourist information. Utterances in dialogues have been previously annotated with a concept-value flat semantics for studying and evaluating spoken...
متن کامل