Dialogue Generation Research Articles

A Step Towards the Future of Role-Playing Games: The SpyFeet Mobile RPG Project

Meaningful choice has often been identified as a key component in a player's engagement with an interactive narrative, but branching stories require tremendous amounts of hand-authored content, in amounts that increase exponentially rather than linearly as more choice points are added. Previous approaches to reducing authorial burden for computer RPGs have relied on creating better tools to manage existing unwieldy structures of quests and dialogue trees. We hypothesize that reducing authorial burden and increasing agency are two sides of the same coin, requiring specific advancements in two related areas of design and technology research: (1) dynamic story management architecture that represents story events abstractly and allows story elements to be selected and re-ordered in response to player choices, and (2) dynamic dialogue generation to allow a single story event to be revealed differently by different characters and in the context of dynamic relationships between those characters and the player. This paper describes SpyFeet, a playable prototype of a storytellingsystem designed to test this hypothesis.

言語資源を用いた非タスク指向型対話システム

In this paper, we propose a non-task-oriented dialog system which uses multiple language resources. This system can generate dynamic dialogues by two methods: one is using the Web; another is using the language resources such as Japanese Google N-grams and Nihongo-goitaikei. First, the system collects Web pages' data by Web retrieval after doing morphological analysis for the user input. Then the system extracts candidate topic terms from the data and determines a way of dialog generation according to the extracted terms. In the case of using Google N-grams, the system generates dialogs by searching N-grams after the terms and connects words recursively. In the case of the Web, the system collects Web pages with extracted words and their referential words. After that, the system generates the sentence by clipping sentence which includes extracted word. We carried out experiments to evaluate the proposed system.

HILDA: A Discourse Parser Using Support Vector Machine Classification

Discourse structures have a central role in several computational tasks, such as question-answering or dialogue generation. In particular, the framework of the Rhetorical Structure Theory (RST) offers a sound formalism for hierarchical text organization. In this article, we present HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification. SVM classifiers are trained and applied to discourse segmentation and relation labeling. By combining labeling with a greedy bottom-up tree building approach, we are able to create accurate discourse trees in linear time complexity. Importantly, our parser can parse entire texts, whereas the publicly available parser SPADE (Soricut and Marcu 2003) is limited to sentence level analysis. HILDA outperforms other discourse parsers for tree structure construction and discourse relation labeling. For the discourse parsing task, our system reaches 78.3% of the performance level of human annotators. Compared to a state-of-the-art rule-based discourse parser, our system achieves a performance increase of 11.6%.

A Non-Modal Approach to Integrating Dialogue and Action

We have developed and demonstrated an experimental authoring and run-time tool, called Disco for Games, that supports the creation of games in which dialogue and action are integrated without the need for changing modes. This tool is based on collaborative discourse theory and hierarchical task networks, in which utterances are treated as actions, and has a number of additional benefits including better modeling of interruptions, automatic dialogue generation, plan recognition and automatic failure retry.

Learning what to say and how to say it: Joint optimisation of spoken dialogue management and natural language generation

This paper argues that the problems of dialogue management (DM) and Natural Language Generation (NLG) in dialogue systems are closely related and can be fruitfully treated statistically, in a joint optimisation framework such as that provided by Reinforcement Learning (RL). We first review recent results and methods in automatic learning of dialogue management strategies for spoken and multimodal dialogue systems, and then show how these techniques can also be used for the related problem of Natural Language Generation. This approach promises a number of theoretical and practical benefits such as fine-grained adaptation, generalisation, and automatic (global) optimisation, and we compare it to related work in statistical/trainable NLG. A demonstration of the proposed approach is then developed, showing combined DM and NLG policy learning for adaptive information presentation decisions. A joint DM and NLG policy learned in the framework shows a statistically significant 27% relative increase in reward over a baseline policy, which is learned in the same way only without the joint optimisation. We thereby show that that NLG problems can be approached statistically, in combination with dialogue management decisions, and we show how to jointly optimise NLG and DM using Reinforcement Learning.

Personalised and self regulated learning in the Web 2.0 era: International exemplars of innovative pedagogy using social software

<blockquote><p>Research findings in recent years provide compelling evidence of the importance of encouraging student control over the learning process as a whole. The socially based tools and technologies of the Web 2.0 movement are capable of supporting informal conversation, reflexive dialogue and collaborative content generation, enabling access to a wide raft of ideas and representations. Used appropriately, these tools can shift control to the learner, through promoting learner agency, autonomy and engagement in social networks that straddle multiple real and virtual learning spaces independent of physical, geographic, institutional and organisational boundaries. As argued in this article, however, in order for self-regulated learning to come to fruition, students need not only to be able to choose and personalise what tools and content are available, but also to have access to the necessary scaffolding to support their learning. Emerging practices with social computing technologies, a number of examples of which are showcased in this article, signal the need for pedagogies that are more personal, social and participatory. The authors conclude with a discussion of some of the key implications for practice, including an outline of the current challenges faced by tertiary educators.</p></blockquote><p> </p>

Supporting Dialogue Generation for Story-Based Games

Providing compelling, realistic, immersive game worlds is one of the major goals in modern game design. The presence of unique and interesting dialogue for all of the characters in a game enhances this sense of immersion. In this paper we present the concept of an “Intentional Dialogue Line” that supports the efficient generation of multiple variations of a dialogue, where these variations are both unique and appropriate to the character who is speaking them. This paper focuses on how machine learning can be used to quickly polines with existing content.

USING THEATRICAL CONCEPTS FOR ROLE-PLAYS WITH EDUCATIONAL AGENTS

ABSTRACT Role-plays with educational agents allow to embed information and educational goals into a narrative context. These agents do not only have to come across as believable and lifelike, they also have to embody the pedagogical principles and educational goals of the application domain. In this paper, we argue that theatrical concepts, namely concepts derived from improvisational theater and meta-theater, can guide the design of educational agents. We illustrate this by presenting two systems: Puppet provides young children with improvisational agents to promote early learning through educational role-plays and CrossTalk uses interactive performances with virtual actors to demonstrate the basic principles that govern automatic dialogue generation. For both systems, we show how the theatrical concepts support a systematic approach to character design, behavior modeling, and user interaction and how they help to increase the believability and lifelikeness of our characters in an educational context.

Natural Conversational Interfaces to Geospatial Databases

AbstractNatural (spoken) language, combined with gestures and other human modalities, provides a promising alternative for interacting with computers, but such benefit has not been explored for interactions with geographical information systems. This paper presents a conceptual framework for enabling conversational human‐GIS interactions. Conversations with a GIS are modeled as human‐computer collaborative activities within a task domain. We adopt a mental state view of collaboration and discourse and propose a plan‐based computational model for conversational grounding and dialogue generation. At the implementation level, our approach is to introduce a dialogue agent,GeoDialogue, between a user and a geographical information server.GeoDialogueactively recognizes user's information needs, reasons about detailed cartographic and database procedures, and acts cooperatively to assist user's problem solving.GeoDialogueserves as a semantic ‘bridge’ between the human language and the formal language that a GIS understands. The behavior of such dialogue‐assisted human‐GIS interfaces is illustrated through a scenario simulating a session of emergency response during a hurricane event.

Pathways less traveled to value creation: interaction, dialogue and knowledge generation

Relationship marketing is based on the idea that the existence of a relationship between customer and supplier creates value for both parties, in addition to the value of the products or services provided. In this special issue edition entitled “Pathways less traveled to value creation: interaction, dialogue and knowledge generation” articles are submitted from five sets of authors, giving different perspectives of marketing and the knowledge generation and communication aspects surrounding it.

An automatic dialogue generation platform for personalized dialogue applications

We explore a voice user interface for human–machine communication that uses a dialogue structure personalized to an individual user, subject to the constraints of the system's resources. Conventional dialogue systems typically use architectures that create a set of predefined speech objects, or subdialogues, by combining several static components, such as grammars and other language components. Such systems are limited because most databases are dynamic, and users have different preferences for topical content and presentation format. Ideally, a dialogue would combine a user's intentions, encoded in a profile, with information and services available in a dynamic and distributed external environment. We use a modular architecture where a centralized Application Generator (AG) interacts with two managers. A user's preferences are stored in a profile handled by a Profile Manager. An Information Manager uses these preferences when accessing external databases and extracting, filtering, or presenting information in a form customized to that particular user. The AG then builds an anticipated dialogue, allowing a user to navigate between a personalized set of services, each of which presents information and services in a manner customized for that user. Therefore, the AG generates, in a uniform and consistent manner, a finite state dialogue for any task described by a set of specifications residing on a distributed network. Finally, a dialogue manager uses a set of protocols to carry out an actual dialogue session with the user.

A decision support system for bank location selection

As the number and size of variables in any business increase, the decision makers must choose among a larger number of alternatives with more constraints. The decision to establish a bank in a new area is a strategic one with many quantifiable and subjective variables. The decision has great influence on bank returns and image. This research objective was to build a decision support system (DSS) to help the decision makers in the banking industry select the most promising bank location in the Amman area. The system consisted of three elements; a database, a model base, and interface. The database contained information about zoning, population, income, number of commercial and industrial entities, capital, potential growth, number of competitors, and the need for bank existence in the area. The model base contained information and formulas of how to evaluate and judge the different inputs whether quantifiable or subjective. Interaction was facilitated using a dialogue generation management system for interfacing. Excel was used for databases, while Visual Basic was used for interfacing.

An Integrated Discourse Recipe-Based Model for Task-Oriented Dialogue

We present an integrated discourse recipe-based model (DRM) for dialogue generation and interpretation. Discourse recipes are generalizations of discourse plans. The DRM has been implemented as part of a conversational agent that supports task-oriented dialogue between human and artificial pilots. The design of the DRM has been strongly influenced by its implementation in the Soar cognitive architecture. In the DRM, discourse recipes are acquired as a side effect of dialogue planning. The discourse recipes can be used for generation and interpretation in future situations in place of planning and reasoning from first principles. We describe the motivation for a discourse recipe-based approach and present the design of the DRM.

Book review: Explanation and Interaction: The Computer Generation of Explanatory Dialogues by Alison Cawsey (MIT Press. 1992)

"Explanatory" is an apt term to describe this book by Alison Cawsey. Her style is perfectly suited to the needs of both experts and novices in the dialogue generation area. Step by step, she leads us through the foremost trends and theories dealing with the development of computer systems for the explanation of pieces of knowledge, examining their advantages, disadvantages and possible applications, while introducing us to the approaches she has taken in the construction of her own system for the generation of explanatory discourse.

DSS structure and algorithmic transparency in APL

Earlier discussion focused on APL as an executable notation for understanding the inner-workings of dialogue generation and data/model base management in Decision Support Systems (DSS). The present work applies the notion of algorithmic transparency to the broader properties of system structure that connect the technology components of DSS. Using a concise set of idioms, embodying only the control construct of sequence, APL's direct definition form is employed in revealing patterns in the specification of a functional prototype Group DSS (GDSS).

A structured approach to designing human-computer dialogues

This article presents a conceptual model and software tool for designing and implementing flexible human-computer dialogues. The tool is referred to as a dialogue generator. The rationale for building such a tool is discussed in the context of other work in the literature, and is based on a fully operational version written in APL. A dialogue generator is important because of the cost of designing dialogues, and the rapidly increasing importance of dialogue generation due to the proliferation of interactive applications of computers. A command language model is used for the target dialogue because of its inherent simplicity, which promotes a structured and streamlined approach based on interaction events, which are described in tabular form in the dialogue data-base. “Help” and “abort” facilities are provided, as are facilities for controlling the flow of the dialogue. The implementation is discussed, particularly in terms of how to represent the various types of information pertaining to an interaction event, and how to store and organize the information. The concepts of user guided and system guided dialogues are re-examined in the context of the flow-control mechanism. Both styles of dialogue are needed, depending on the user, and both can be covered by the model described. The model is compared with others in the literature, and its capabilities are evaluated against published rules for dialogue programming.