Referential success depends on choice of referring expression. The choice of referring expression will depend on contextual factors as well as factors related to speaker and addressee knowledge. A shared-learning paradigm was used in which partners learned names of objects together and separately before a referential task. Items differed on commonality, with some independently rated as more com...

As dialog systems evolve to handle unconstrained input and for use in open environments, addressee detection (detecting speech to the system versus to other people) becomes an increasingly important challenge. We study a corpus in which speakers talk both to a system and to each other, and model two dimensions of speaking style that talkers modify when changing addressee: speech rhythm and voca...

While the communicative approach to law is spread widely today, characteristic of legal communication are still purely described and weakly researched. Linguists experts in theory not involved discourse notions practice law, whereas jurists ready step out this discourse. This article represents an attempt overcome these difficulties find necessary parameters (focusing on figure addressee), bein...

The study of norms (Ns) is recent but growing concern in the AI field (cf. [MOS92]; [SHO92]) as well within other formal approaches to social action, such as Game Theory (where theories of Ns began to appear long before, cf.[LEW69]; [ULL77]). The normative is an essential dimension of social life. An explicit model of such dimension is crucial for any theory of social action. Notions such as "s...

The necessity of addressee detection arises in multiparty spoken dialogue systems which deal with human-human-computer interaction. In order to cope with this kind of interaction, such a system is supposed to determine whether the user is addressing the system or another human. The present study is focused on multimodal addressee detection and describes three levels of speech and text analysis:...

To communicate cooperatively, speakers must determine what constitutes the common ground with their addressee and adapt their referential choices accordingly. Assessing another person's knowledge requires a social cognition ability termed theory of mind (ToM). This study relies on a novel referential communication task requiring probabilistic inferences of the knowledge already held by an addre...

let$ p_{n}(x)= sum_{i=0}^{n} a_{i}x^{i}$ be a random algebraicpolynomial, where $a_{0},a_{1}, cdots $ is a sequence of independent random variables belong to the domain of attraction of the normal law. thus $a_j$'s for $j=0,1cdots $ possesses the characteristic functions $exp {-frac{1}{2}t^{2}h_{j}(t)}$, where $h_j(t)$'s are complex slowlyvarying functions.under the assumption that th...

Addressee detection for dialog systems aims to detect which utterances are directed at the system, as opposed to someone else. An important means for classification is the lexical content of the utterance, and N-gram models have been shown to be effective for this task. In this paper we investigate whether neural networks can enhance lexical addressee detection, using data from a human-human-co...