Figure 2 - uploaded by Feiyu Xu
Content may be subject to copyright.
Our bartender NPC in his bar in Twinity

Our bartender NPC in his bar in Twinity

Source publication
Conference Paper
Full-text available
This paper describes the KomParse system, a natural-language dialog system in the three-dimensional virtual world Twinity. In order to fulfill the various communication demands between nonplayer characters (NPCs) and users in such an online virtual world, the system realizes a flexible and hybrid approach combining knowledge-intensive domain-specif...

Similar publications

Conference Paper
Full-text available
This article explores identification with non-anthropomorphic avatars in a virtual reality game and its relationship to arousal and valence. Fifty-six male and female participants played a virtual game in a 360º stereoscopic immersive interactive visualization environment using either body movement or a joystick. A scale was developed to test ident...
Article
Full-text available
Virtual characters (including educational pedagogy agents and NPCs in games) are significant endeavors to benefit students' learning in technology-enhanced learning. In this paper, we propose a concept of character-driven learning, to address two related issues: how to establish close relationship with virtual characters and how to enhance students...

Citations

... On the other hand, dialog modeling through finite state graphs is very robust, see Cohen (1997) for more information. • Frame based: the dialog is controlled by a hidden electronic form, collecting information from the user (Aust et al., 1995;Constantinides et al., 1998;Klüwer et al., 2010). An example application could be a travel-support hotline, delivering information about train schedules to a user. ...
Chapter
This chapter provides an overview of the technologies used for chatbots on the one hand and research dialog systems on the other hand. By comparing the two, the main disadvantage of chatbots is shown: its dependency on huge amounts of inflexible language data. Methods originating from Computational Linguistics, which are frequently used in dialog systems, can provide a solution by offering further flexibility to the language processing part of the system.
... That means that it is more representative for the data that human learners get, and that our methods can be applied to a wider variety of data, possibly also to datasets that have not been collected specifically for this purpose. A related project is KomParse (Klüwer et al., 2010). Piantadosi et al. (2008) developed a Bayesian model that learns compositional semantic meanings of different kinds of words, including quantifiers, but from completely artificial data. ...
Article
Full-text available
We use data from a virtual world game for automated learning of words and grammatical con-structions and their meanings. The language data are an integral part of the social interaction in the game and consist of chat dialogue, which is only constrained by the cultural context, as set by the nature of the provided virtual environment. Building on previous work, where we extracted a vocab-ulary for concrete objects in the game by making use of the non-linguistic context, we now target NP/DP grammar, in particular determiners. We assume that we have captured the meanings of a set of determiners if we can predict which determiner will be used in a particular context. To this end we train a classifier that predicts the choice of a determiner on the basis of features from the linguistic and non-linguistic context.
... The work presented in this paper is part of a dialogue system called KomParse (Klüwer et al., 2010), which is an application of a NL dialogue system combined with various question answering technologies in a three-dimensional virtual world named Twinity, a web-based online product of the Berlin startup company Metaversum 1 . The Kom- Parse NPCs provide various services through conversation with game users such as selling pieces of furniture to users via text based conversation. ...
Conference Paper
Full-text available
This paper presents a novel approach to dialogue act recognition employing multilevel information features. In addition to features such as context information and words in the utterances, the recognition task utilizes syntactic and semantic relations acquired by information extraction methods. These features are utilized by a Bayesian network classifier for our dialogue act recognition. The evaluation results show a clear improvement from the accuracy of the baseline (only with word features) with 61.9% to an accuracy of 67.4% achieved by the extended feature set.
In most role-playing games (RPGs), non-player characters (NPCs) tend to have most initiative in conversation between the players and the NPCs. The NPCs are mainly talking to lead the players along the storylines of games, and sometimes ask the player to answer simple questions. Such a unilateral conversation is unnatural and unrealistic, and consequently, it is concerned that the player’s sense of immersion into the game will decrease. In order to improve the reality of the conversation, this study proposed a conversation method whereby an NPC adaptively switch the initiative according to the players’ preference of which of the player and the NPC has the initiative. To confirm the effect of this method, we conducted an experiment in which the participants talked with an NPC in a game scenario. This experiment compared the proposed method with the existing method that an NPC has the most initiative and the method that an NPC randomly switches the initiative. The result of the experiment suggested that the proposed method can decrease the unilateral impression compared with the existing method. Furthermore, the result also showed a probability that the proposed method motivates the players to talk to the NPC.
Conference Paper
In most role-playing games, a non-player character (NPC) tends to have the most initiative, i.e., developing conversation topics, on the dialog. Thus, the player tends to experience a unilateral impression, i.e., the feeling of that an NPC forces conversation topics on the player in spite of the player's willingness, and gradually loses his/her motivation to communicate with an NPC. In order to address this problem, this study proposes a dialog method whereby an NPC can adaptively switch the initiative by determining the player's willingness to talk/listen to the NPC. Based on the results of an evaluation experiment in which the participants talked with the NPC in the game scenario, it is suggested that the aspect of mixed-initiative in our proposed method could decrease the unilateral impression associated with the existing method that an NPC has the most initiative. Furthermore, the determination of the player's desire in our proposed method could further motivate players to talk to the NPC.