Susan Weber McRoy

Repairing conversational misunderstandings and non-understandings

Abstract Participants in a discourse sometimes fail to understand one another, but, when aware of the problem, collaborate upon or negotiate the meaning of a problematic utterance. To address non-understanding, we have developed two plan-based models of collaboration in identifying the correct referent of a description: one covers situations where both conversants know of the referent, and the other covers situations, such as direction-giving, where the recipient does not. In the models, conversants use the mechanisms of refashioning, suggestion and elaboration, to collaboratively refine a referring expression until it is successful. To address misunderstanding, we have developed a model that combines intentional and social accounts of discourse to support the negotiation of meaning. The approach extends intentional accounts by using expectations deriving from social conventions in order to guide interpretation. Reflecting the inherent symmetry of the negotiation of meaning, all our models can act as both speaker and hearer, and can play both the role of the conversant who is not understood or misunderstood and the role of the conversant who fails to understand.

The biomedical discourse relation bank

BackgroundIdentification of discourse relations, such as causal and contrastive relations, between situations mentioned in text is an important task for biomedical text-mining. A biomedical text corpus annotated with discourse relations would be very useful for developing and evaluating methods for biomedical discourse processing. However, little effort has been made to develop such an annotated resource.ResultsWe have developed the Biomedical Discourse Relation Bank (BioDRB), in which we have annotated explicit and implicit discourse relations in 24 open-access full-text biomedical articles from the GENIA corpus. Guidelines for the annotation were adapted from the Penn Discourse TreeBank (PDTB), which has discourse relations annotated over open-domain news articles. We introduced new conventions and modifications to the sense classification. We report reliable inter-annotator agreement of over 80% for all sub-tasks. Experiments for identifying the sense of explicit discourse connectives show the connective itself as a highly reliable indicator for coarse sense classification (accuracy 90.9% and F1 score 0.89). These results are comparable to results obtained with the same classifier on the PDTB data. With more refined sense classification, there is degradation in performance (accuracy 69.2% and F1 score 0.28), mainly due to sparsity in the data. The size of the corpus was found to be sufficient for identifying the sense of explicit connectives, with classifier performance stabilizing at about 1900 training instances. Finally, the classifier performs poorly when trained on PDTB and tested on BioDRB (accuracy 54.5% and F1 score 0.57).ConclusionOur work shows that discourse relations can be reliably annotated in biomedical text. Coarse sense disambiguation of explicit connectives can be done with high reliability by using just the connective as a feature, but more refined sense classification requires either richer features or more annotated data. The poor performance of a classifier trained in the open domain and tested in the biomedical domain suggests significant differences in the semantic usage of connectives across these domains, and provides robust evidence for a biomedical sublanguage for discourse and the need to develop a specialized biomedical discourse annotated corpus. The results of our cross-domain experiments are consistent with related work on identifying connectives in BioDRB.

Interactive Computerized Health Care Education

The Patient Education and Activation System (PEAS) project aims to prepare people to take a more active role in their health care decisions. In this paper, the authors describe their work on the Layman Education and Activation Form (LEAF). LEAF is designed to be an interactive, Internet-based system for collecting a patients medical history. It is unique in that it gives patients access to educational information when it is most pertinent, while they are attempting to complete a form. It avoids overwhelming the patient, by providing information only when it is likely to be relevant. The system avoids asking irrelevant questions or providing irrelevant facts by tailoring the content of the form to the patients responses. The system also uses the patients answers to suggest questions that the patient might ask a doctor and provides online resources that the patient can browse. n JAMIA. 1998;5:347 - 356.

An augmented template-based approach to text realization

We present an Augmented Template-Based approach to text realization that addresses the requirements of real-time, interactive systems such as a dialog system or an intelligent tutoring system. Template-based approaches are easier to implement and use than traditional approaches to text realization. They can also generate texts more quickly. However traditional template-based approaches with rigid templates are inflexible and difficult to reuse. Our approach augments traditional template-based approaches by adding several types of declarative control expressions and an attribute grammar-based mechanism for processing missing or inconsistent slot fillers. Therefore, augmented templates can be made more general than traditional ones, yielding templates that are more flexible and reusable across applications.

Race-Based Parsing and Syntactic Disambiguation

We present a processing model that integrates same important psychological claims about the human sentence-parsing mechanism: namely, that processing is influenced by limitations an working memory and by various syntactic preferences. The model uses time-constraint information to resolve conflicting preferences in a psychologically plausible way. The starting paint far this proposal is the Sausage Machine model (Fodor & Frazier, 1980: Frazier & Fodor, 1978). From there, we attempt to overcome the original models dependence an ad hoc aspects of its grammar, and its omission of verb-frame preferences. We also add mechanisms far lexical disambiguation and semantic processing in parallel with syntactic processing.

Abductive explanation of dialogue misunderstandings

To respond to an utterance, a listener must interpret what others have said and why they have said it. Misunderstandings occur when agents differ in their beliefs about what has been said or why. Our work combines intentional and social accounts of discourse, unifying theories of speech act production, interpretation, and the repair of misunderstandings. A unified theory has been developed by characterizing the generation of utterances as default reasoning and using abduction to characterize interpretation and repair.

A two-way text-messaging system answering health questions for low-income pregnant women

OBJECTIVE The purpose of the study was to gauge the effectiveness of a low-cost, automated, two-way text-messaging system to distribute pregnancy and health-related information to low-income expectant women. METHODS In total, 20 participants were recruited for a one-month intervention involving the use of cell phones to text pregnancy-related questions to the system. Participants received either a direct answer or encouragement to seek answers from health care providers. Pre- and post-tests as well as a focus group at the end of the intervention were conducted. RESULTS Participants uniformly found the system easy to use and accessible. Using the system increased levels of perceived pregnancy-related knowledge and facilitated patient-provider communication. Moreover, participants reported significant reductions in stress and depression and improved mental health after using the system. The system responded to most known questions quickly and accurately, and also encountered many new topics and linguistic expressions. CONCLUSION Overall, the data indicated that the text messaging system offered psychological benefits and promoted health communication by providing health information and encouraging patient-provider communication. PRACTICE IMPLICATIONS An automated, two-way text messaging system is an efficient, cost-effective, and acceptable method for providing health information to low-income pregnant women.

Information Needs, Seeking Behaviors, and Support Among Low-Income Expectant Women

Previous studies have consistently found associations between low income and infant health outcomes. Moreover, although health information-seeking is a maternal behavior related to improved health outcomes, little is known about the health information-seeking behaviors and information needs of low-income pregnant women. The purpose of the current investigation was to examine the information needs, information-seeking behaviors, and perceived informational support of low-income pregnant women. Accordingly, the study recruited 63 expectant women enrolled in a subsidized prenatal care program in Milwaukee, Wisconsin, during two time periods: March–May 2011 and October–December 2011. Results indicated that participants relied heavily upon interpersonal sources of information, especially family and the father of the baby; rarely used the Internet for health-related information; and desired information beyond infant and maternal health, such as finding jobs and accessing community/government resources. Participants who used family members as primary sources of information also had significantly increased levels of perceived informational support and reduced uncertainty about pregnancy. Our findings have implications for the dissemination of pregnancy-related health information among low-income expectant women.

Computational Models of Mixed-Initiative Interaction

Computational Models of Mixed-Initiative Interaction brings together research that spans several disciplines related to artificial intelligence, including natural language processing, information retrieval, machine learning, planning, and computer-aided instruction, to account for the role that mixed initiative plays in the design of intelligent systems. The ten contributions address the single issue of how control of an interaction should be managed when abilities needed to solve a problem are distributed among collaborating agents. Managing control of an interaction among humans and computers to gather and assemble knowledge and expertise is a major challenge that must be met to develop machines that effectively collaborate with humans. This is the first collection to specifically address this issue.

Enriching partially-specified representations for text realization using an attribute grammar

We present a new approach to enriching under-specified representations of content to be realized as text. Our approach uses an attribute grammar to propagate missing information where needed in a tree that represents the text to be realized. This declaratively-specified grammar mediates between application-produced output and the input to a generation system and, as a consequence, can easily augment an existing generation system. End-applications that use this approach can produce high quality text without a fine-grained specification of the text to be realized, thereby reducing the burden to the application. Additionally, representations used by the generator are compact, because values that can be constructed from the constraints encoded by the grammar will be propagated where necessary. This approach is more flexible than defaulting or making a statistically good choice because it can deal with long-distance dependencies (such as gaps and reflexive pronouns). Our approach differs from other approaches that use attribute grammars in that we use the grammar to enrich the representations of the content to be realized, rather than to generate the text itself. We illustrate the approach with examples from our template-based text-realizer, YAG.