Jennifer Chu-Carroll

Question Answering Using Constraint Satisfaction: QA-By-Dossier-With-Contraints

QA-by-Dossier-with-Constraints is a new approach to Question Answering whereby candidate answers confidences are adjusted by asking auxiliary questions whose answers constrain the original answers. These constraints emerge naturally from the domain of interest, and enable application of real-world knowledge to QA. We show that our approach significantly improves system performance (75% relative improvement in F-measure on select question types) and can create a dossier of information about the subject matter in the original question.

MIMIC: An Adaptive Mixed Initiative Spoken Dialogue System for Information Queries

This paper describes MIMIC, an adaptive mixed initiative spoken dialogue system that provides movie showtime information. MIMIC improves upon previous dialogue systems in two respects. First, it employs initiative-oriented strategy adaptation to automatically adapt response generation strategies based on the cumulative effect of information dynamically extracted from user utterances during the dialogue. Second, MIMICs dialogue management architecture decouples its initiative module from the goal and response strategy selection processes, providing a general framework for developing spoken dialogue systems with different adaptation behavior.

Tracking Initiative in Collaborative Dialogue Interactions

In this paper, we argue for the need to distinguish between task and dialogue initiatives, and present a model for tracking shifts in both types of initiatives in dialogue interactions. Our model predicts the initiative holders in the next dialogue turn based on the current initiative holders and the effect that observed cues have on changing them. Our evaluation across various corpora shows that the use of cues consistently improves the accuracy in the systems prediction of task and dialogue initiative holders by 2-4 and 8-13 percentage points, respectively, thus illustrating the generality of our model.

An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions

In this paper, we argue for the need to distinguish between task initiative and dialogue initiative, and present an evidential model for tracking shifts in both types of initiatives in collaborative dialogue interactions. Our model predicts the task and dialogue initiative holders for the next dialogue turn based on the current initiative holders and the effect that observed cues have on changing them. Our evaluation across various corpora shows that the use of cues consistently provides significant improvement in the systems prediction of task and dialogue initiative holders. Finally, we show how this initiative tracking model may be employed by a dialogue system to enable the system to tailor its responses to user utterances based on application domain, systems role in the domain, dialogue history, and user characteristics.

Conflict resolution in collaborative planning dialogs

In a collaborative planning environment in which the agents are autonomous and heterogeneous, it is inevitable that discrepancies in the agents beliefs result in conflicts during the planning process. In such cases, it is important that the agents engage in collaborative negotiation to resolve the detected conflicts in order to determine what should constitute their shared plan of actions and shared beliefs. This paper presents a plan-based model for conflict detection and resolution in collaborative planning dialogs. Our model specifies how a collaborative system should detect conflicts that arise between the system and its user during the planning process. If the detected conflicts warrant resolution, our model initiates collaborative negotiation in an attempt to resolve the conflicts in the agents beliefs. In addition, when multiple conflicts arise, our model identifies and addresses the most effective aspect in its pursuit of conflict resolution. Furthermore, by capturing the collaborative planning process in a recursive Propose?Evaluate?Modify cycle of actions, our model is capable of handling embedded negotiation during conflict resolution.

Response Generation in Collaborative Negotiation

In collaborative planning activities, since the agents are autonomous and heterogenous, it is inevitable that conflicts arise in their beliefs during the planning process. In cases where such conflicts are relevant to the task at hand, the agents should engage in collaborative negotiation as an attempt to square away the discrepancies in their beliefs. This paper presents a computational strategy for detecting conflicts regarding proposed beliefs and for engaging in collaborative negotiation to resolve the conflicts that warrant resolution. Our model is capable of selecting the most effective aspect to address in its pursuit of conflict resolution in cases where multiple conflicts arise, and of selecting appropriate evidence to justify the need for such modification. Furthermore, by capturing the negotiation process in a recursive Propose-Evaluate-Modify cycle of actions, our model can successfully handle embedded negotiation subdialogues.

On natural language call routing

Automated call routing is the process of associating a users request with the desired destination. Although some of the call routing functions can often be accomplished though the use of a touch-tone menu in an interactive voice response system, the interaction between the user and such a system is typically very limited. It is therefore desirable to have a call routing system that takes natural language spoken inputs from the user and asks for additional information to complete the users request as a human agent would. In this paper we present a recent study on natural language call routing and discuss the capabilities and limitations of current technologies.

Constructing and Utilizing a Model of User Preferences in Collaborative Consultation Dialogues

A natural language collaborative consultation system must take user preferences into account. A model of user preferences allows a system to appropriately evaluate alternatives using criteria of importance to the user. Additionally, decision research suggests both that an accurate model of user preferences could enable the system to improve a users decision‐making by ensuring that all important alternatives are considered, and that such a model of user preferences must be built dynamically by observing the users actions during the decision‐making process. This paper presents two strategies: one for dynamically recognizing user preferences during the course of a collaborative planning dialogue and the other for exploiting the model of user preferences to detect suboptimal solutions and suggest better alternatives. Our recognition strategy utilizes not only the utterances themselves but also characteristics of the dialogue in developing a model of user preferences. Our generation strategy takes into account both the strength of a preference and the closeness of a potential match in evaluating actions in the users plan and suggesting better alternatives. By modeling and utilizing user preferences, our system is able to fulfill its role as a collaborative agent.

Dialogue Management in Vector-Based Call Routing

This paper describes a domain independent, automatically trained call router which directs customer calls based on their response to an open-ended How may I direct your call? query. Routing behavior is trained from a corpus of transcribed and hand-routed calls and then carried out using vector-based information retrieval techniques. Based on the statistical discriminating power of the n-gram terms extracted from the callers request, the caller is 1) routed to the appropriate destination, 2) transferred to a human operator, or 3) asked a disambiguation question. In the last case, the system dynamically generates queries tailored to the callers request and the destinations with which it is consistent. Our approach is domain independent and the training process is fully automatic. Evaluations over a financial services call center handling hundreds of activities with dozens of destinations demonstrate a substantial improvement on existing systems by correctly routing 93.8% of the calls after punting 10.2% of the calls to a human operator.

Conflict detection and resolution in collaborative planning

In multi-agent collaborative planning, since each agent is autonomous and heterogeneous, it is inevitable that conflicts arise among the agents during the planning process. A collaborative agent, however, must be capable of detecting and resolving these conflicts. This paper describes a computational model that captures the collaborative planning process in a Propose-Evaluate-Modify cycle of actions. Our model is capable of evaluating a given proposal to detect potential conflicts regarding both proposed actions and proposed beliefs, and of initiating collaborative negotiation subdialogues to resolve the detected conflicts. In situations where multiple conflicts arise, our model identifies the focus of the modification process and selects appropriate evidence to justify the necessity for such modification. Finally, our model handles the negotiation of proposed domain actions, proposed problem-solving actions, and proposed beliefs in a unified manner.