The Partially Observable Markov Decision Process (POMDP) provides a rich mathematical model for designing agents that have to formulate plans under uncertainty. The curses of dimensionality and history associated with solving POMDPs have lead to numerous refinements of the value iteration algorithm. Several exact methods with different pruning strategies have been devised, yet, limited scalability has lead research to focus on ways to approximate the optimal value function. One set of approximations relies on point-based value iteration, which maintains a fixed-size value function, and is typically executed offline. Another set of approximations relies on tree search, which explores the implicit tree defined by the value iteration equation, and is typically executed online. In this paper we present a hybrid value iteration algorithm that combines the benefits of point-based value iteration and tree search. Using our approach, a hybrid agent executes tree search online, and occasionally updates its offline-computed lower bound on the optimal value function, resulting in improved lookahead and higher obtained reward, while meeting real-time constraints. Thus, unlike other hybrid algorithms that use an invariant value function computed offline, our proposed scheme uses information from the real-time tree search process to reason whether to perform a point-based backup online. Keeping track of partial results obtained during online planning makes the computation of point-based backups less prohibitive. We report preliminary results that support our approach.

Creating natural language tutorial dialogue systems that realize effective strategies is a central challenge for intelligent tutoring systems research. Traditional approaches generally require large development time, do not generalize well across domains, and do not match the flexibility and natural language sophistication of human tutors. A promising approach that may offer several benefits is data-driven system development, in which a dialogue policy is learned from corpora of human tutorial dialogue. To date these learning approaches typically focus on optimizing the tutor’s choice of act, and do not explicitly model the instances in which the tutor chose not to act. This paper reports on a hidden Markov modeling (HMM) approach within human textual tutorial dialogue that explicitly represents the tutors’ choices not to intervene. The results show that an HMM that models tutor non-interventions predicts tutor moves significantly better than a model that does not explicitly represent the non-interventions. The findings have implications for automatically modeling tutorial strategies and for learning dialogue policies from corpora.

This paper describes preliminary research in the use of ontological knowledge for the task of automatically classifying classical Chinese poetry (CCCP) according to authorship. Based on a collection of poems written by Liu Yong (987–1053 AD) and Su Shi (1037– 1101 AD), which have been analyzed according to a taxonomy of ontological entities at the lexical level, the research looks into the issue of whether characteristic features can be automatically extracted as important stylistic differences between the two poets. This paper examines the efficiency of different ontological concepts as features in CCCP using Support Vector Machine (SVMs). The experiment shows that an integration of ontological knowledge and bags-of-words (BoW) produces a higher precision for CCCP than BoW only with an overall increase of 2.1% and 2.2% in terms of precision and F-score.

This paper presents our explorations in using graph centrality measures to solve the synonym expansion problem. In particular, we use the concept of directional similarity to derive directed graphs on which we apply centrality algorithms to identify the most likely synonyms for a target word in a given context. We show that our method can lead to performance comparable to the state-of-the-art.

Could we enrich speech-act theory to deal with discourse? Wittgenstein and Searle are sceptical. In my view, the primary aim of discourse pragmatics is to analyze the structure and dynamics of language-games with an internal conversational goal. Logic can analyze felicity-conditions of such collective illocutions. For interlocutors obey systems of constitutive rules in conducting descriptive, deliberative, declaratory or expressive dialogues. I will show how to construct speaker-meaning from sentence-meaning, conversational background and maxims. I will also explain how to use the resources of formalisms and mathematical logic and to further develop intensional and illocutionary logics, the logic of attitudes and of action in order to characterize our ability to converse. I will also deal with the nature of intelligent dialogues between man and machines in A.I.

We have experimented with the notion of — conceptualization, and contextualization from situated cognition and psychic reflection from activity theory for identifying context into a method called the activity states framework (ASF). The purpose of the ASF is to provide a method of analysis for identifying collaborators activity during situated context − specific to Web-mediated collaboration. This paper introduces the ASF.

Using the Gramulator, we analyzed the linguistic features of ESL texts and fairy tales. Our goal was to determine if fairy tales had the potential to be used as reading material for English language learners. The results of our analyses suggest that there are significant similarities between fairy tales and ESL texts, but that differences lie in the content of the text types with fairy tales appearing significantly more narrative in style and ESL texts appearing more expository.

The paper deals with the problem of an analysis of complex sentences in Czech on the basis of manually annotated data. The availability of a specialized corpus explicitly describing mutual relationships between segments and clauses in Czech complex sentences, together with the availability of a thoroughly syntactically annotated corpus, the Prague Dependency Treebank, provide a solid background for linguistic investigation. The paper presents quantitative, linguistic and structural observations which provide a number of clues for building an algorithm for analyzing a structure of complex sentences in the future.

The aim of this paper is threefold: (1) it explores methods for the detection of affective states in text, (2) it presents the usage of such affective cues in a conversational system and (3) it evaluates its effectiveness in a virtual reality setting. Valence and arousal values, used for generating facial expressions of users' avatars, are also incorporated into the dialog, helping to bridge the gap between textual and visual modalities. The system is evaluated in terms of its ability to: (i) generate a realistic dialog, (ii) create an enjoyable chatting experience, and (iii) establish an emotional connection with participants. Results show that user ratings for the conversational agent match those obtained in a Wizard of Oz setting.

The hyper-modular printer control project at PARC has proven that a tightly integrated model-based planning and control framework can effectively control a complex physical system. Recently, we have successfully applied this framework to another application: planning for the Material Control System (MCS) of Liquid Crystal Display (LCD) manufacturing plant in a joint project between the Embedded Reasoning Area at PARC and the Products Development Center at the IHI Corporation. The model-based planner created at PARC was able to successfully solve a diverse set of test scenarios provided by IHI, including those that were deemed very difficult by the IHI experts. The short projecttime (2 months) proved that model-based planning is a flexible framework that can adapt quickly to novel applications. In this paper, we will introduce this complex domain and describe the adaptation process of the Plantrol online planner. The main contributions are: (1) introducing a successful application of general-purpose planning; (2) outline the timeline-based online temporal planner; and (3) description of a complex warehouse management problem that can serve as an attractive benchmark domain for planning.