Traditionally, the most imPortant input to the dialogue management component of a natural language system are semantic representations (e.g., formulae of first-order predicate calculus). Only recently, other kinds of information (e.g., phonetic transcriptions of unknown words) has been used. There is, however, room for the utilization of additional knowledge sources. In what follows, we first e...

Emoji is an essential component in dialogues which has been broadly utilized on almost all social platforms. It could express more delicate feelings beyond plain texts and thus smooth the communications between users, making dialogue systems more anthropomorphic and vivid. In this paper, we focus on automatically recommending appropriate emojis given the contextual information in multiturn dial...

In this paper we discuss the adaptive User Model component of the AthosMail system, and describe especially the Cooperativity Model which produces recommendations for the appropriate explicitness of the system utterances, depending on the user’s observed competence levels. The Cooperativity Model deals with the system’s dialogue control and explicitness of the given information: these two aspec...

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and make cross-domain, multi-lingual dialogue systems intractable. Moreover, human languages are context-aware. The most natural response should be directly learne...